diff --git a/fern/apis/api/ai_examples_override.yml b/fern/apis/api/ai_examples_override.yml index 9c5857d00..bed285b49 100644 --- a/fern/apis/api/ai_examples_override.yml +++ b/fern/apis/api/ai_examples_override.yml @@ -249,59 +249,6 @@ paths: itemsBeyondRetention: false createdAtLe: '2024-01-15T09:30:00Z' createdAtGe: '2023-12-01T00:00:00Z' - /observability/scorecard: - get: - x-fern-examples: - - response: - body: - results: - - id: a3f1c9e2-7b4d-4f8a-9d2e-5b6c7d8e9f01 - orgId: org-1234567890abcdef - createdAt: '2024-01-15T09:30:00Z' - updatedAt: '2024-01-15T09:30:00Z' - name: Customer Support Quality Scorecard - description: Scorecard to evaluate customer support call quality based on key metrics. - metrics: - - structuredOutputId: metric-voice_clarity_001 - conditions: - - comparator: '>=' - value: 90 - points: 50 - description: Voice clarity score above 90 - - comparator: < - value: 90 - points: 20 - description: Voice clarity score below 90 - assistantIds: - - assistant-9876543210fedcba - metadata: - itemsPerPage: 10 - totalItems: 25 - currentPage: 1 - itemsBeyondRetention: false - createdAtLe: '2024-01-15T09:30:00Z' - createdAtGe: '2023-12-01T00:00:00Z' - post: - x-fern-examples: - - request: - metrics: - - structuredOutputId: call_duration_seconds - conditions: - - {} - response: - body: - id: a1b2c3d4-e5f6-7890-ab12-cd34ef567890 - orgId: org-1234567890 - createdAt: '2024-01-15T09:30:00Z' - updatedAt: '2024-01-15T09:30:00Z' - name: Customer Support Call Quality - description: Scorecard to evaluate the quality of customer support calls based on call duration and resolution metrics. - metrics: - - structuredOutputId: call_duration_seconds - conditions: - - {} - assistantIds: - - assistant-9876543210 /reporting/insight: get: x-fern-examples: @@ -393,45 +340,6 @@ paths: pronunciation: prəˌnʌnsiˈeɪʃən language: en-US version: 1.2.3 - /structured-output/run: - post: - x-fern-examples: - - request: - callIds: - - call_9f8b7c6d5e4a3b2c1d0e - response: - body: - type: ai - regex: '' - model: - provider: openai - model: gpt-5.4 - temperature: 1.1 - maxTokens: 5030 - compliancePlan: - forceStoreOnHipaaEnabled: false - id: so_123e4567-e89b-12d3-a456-426614174000 - orgId: org_987f6543-e21b-45d3-b789-123456789abc - createdAt: '2024-01-15T09:30:00Z' - updatedAt: '2024-01-15T09:30:00Z' - name: Customer Feedback Extraction - description: Extracts structured customer feedback data from call transcripts for sentiment analysis and follow-up actions. - assistantIds: - - assistant_abc123def456 - workflowIds: - - workflow_xyz789ghi012 - schema: - type: object - items: {} - properties: {} - description: Schema defining the structure of extracted customer feedback including sentiment, topics, and action items. - pattern: '' - format: date-time - required: - - sentiment - - feedbackDate - enum: [] - title: CustomerFeedbackSchema /reporting/insight/id/run: post: x-fern-examples: @@ -629,91 +537,6 @@ paths: name: Verified User Flow Eval description: This eval checks if the user flow is verified. type: chat.mockConversation - /structured-output: - post: - x-fern-examples: - - request: - name: Customer Feedback Extraction - response: - body: - type: ai - regex: \b(feedback|review|comment)\b - model: - provider: openai - model: gpt-5.4 - temperature: 1.1 - maxTokens: 5030 - compliancePlan: - forceStoreOnHipaaEnabled: false - id: a1b2c3d4-e5f6-7890-abcd-ef1234567890 - orgId: org-9876543210 - createdAt: '2024-01-15T09:30:00Z' - updatedAt: '2024-01-15T09:30:00Z' - name: Customer Feedback Extraction - description: Extracts customer feedback data from conversations for sentiment analysis and reporting. - assistantIds: - - assistant-1234abcd - workflowIds: - - workflow-5678efgh - schema: - type: object - items: {} - properties: {} - description: Schema defining the structure of extracted customer feedback data. - pattern: ^[A-Za-z0-9 ,.!?'-]+$ - format: date-time - required: - - feedbackText - - timestamp - enum: - - positive - - neutral - - negative - title: CustomerFeedbackSchema - get: - x-fern-examples: - - response: - body: - results: - - type: ai - regex: \d{3}-\d{2}-\d{4} - model: - provider: openai - model: gpt-5.4 - temperature: 1.1 - maxTokens: 5030 - compliancePlan: - forceStoreOnHipaaEnabled: false - id: a1b2c3d4-e5f6-7890-abcd-ef1234567890 - orgId: org-9876543210 - createdAt: '2024-01-15T09:30:00Z' - updatedAt: '2024-01-15T09:30:00Z' - name: Customer SSN Extractor - description: Extracts Social Security Numbers from conversation transcripts for identity verification purposes. - assistantIds: - - assistant-1234abcd - workflowIds: - - workflow-5678efgh - schema: - type: string - items: {} - properties: {} - description: A string matching the US Social Security Number format. - pattern: ^\d{3}-\d{2}-\d{4}$ - format: date-time - required: - - ssn - enum: - - 123-45-6789 - - 987-65-4321 - title: SSN Schema - metadata: - itemsPerPage: 10 - totalItems: 50 - currentPage: 1 - itemsBeyondRetention: false - createdAtLe: '2024-01-15T09:30:00Z' - createdAtGe: '2023-12-01T00:00:00Z' /analytics: post: x-fern-examples: @@ -752,3 +575,325 @@ paths: name: Verified User Flow Eval description: This eval checks if the user flow is verified. type: chat.mockConversation + /call/id/customer-recording: + get: + x-fern-examples: + - path-parameters: + id: id + /call/id/pcap: + get: + x-fern-examples: + - path-parameters: + id: id + /call/id/assistant-recording: + get: + x-fern-examples: + - path-parameters: + id: 3fa85f64-5717-4562-b3fc-2c963f66afa6 + /call/id/stereo-recording: + get: + x-fern-examples: + - path-parameters: + id: 3fa85f64-5717-4562-b3fc-2c963f66afa6 + /call/id/video-recording: + get: + x-fern-examples: + - path-parameters: + id: id + /call/id/mono-recording: + get: + x-fern-examples: + - path-parameters: + id: 3fa85f64-5717-4562-b3fc-2c963f66afa6 + /call/id/call-logs: + get: + x-fern-examples: + - path-parameters: + id: id + /reporting/board/id: + delete: + x-fern-examples: + - path-parameters: + id: id + response: + body: + items: + - type: insight + insightId: a3f1c9d2-4b7e-4f8a-9c3d-2e5b7f6a8d9e + systemKey: sys-key-12345 + position: + x: 2 + 'y': 3 + size: + width: 4 + height: 2 + id: d290f1ee-6c54-4b01-90e6-d701748f0851 + orgId: org-7890abcd-1234-5678-efgh-9012ijklmnop + createdAt: '2024-01-15T09:30:00Z' + updatedAt: '2024-04-20T15:45:00Z' + systemKey: system-board-001 + name: Sales Performance Dashboard + layout: + columns: 6 + timeRangeOverride: + step: day + start: '-30d' + end: now + timezone: America/New_York + patch: + x-fern-examples: + - path-parameters: + id: id + response: + body: + items: + - type: insight + insightId: a1b2c3d4-e5f6-7890-ab12-cd34ef567890 + systemKey: sys_insight_001 + position: + x: 2 + 'y': 3 + size: + width: 4 + height: 3 + id: f47ac10b-58cc-4372-a567-0e02b2c3d479 + orgId: 9f8e7d6c-5b4a-3210-9876-54321fedcba0 + createdAt: '2024-01-15T09:30:00Z' + updatedAt: '2024-04-20T14:45:00Z' + systemKey: board_sys_123 + name: Sales Performance Dashboard + layout: + columns: 6 + timeRangeOverride: + step: day + start: '-7d' + end: now + timezone: UTC + get: + x-fern-examples: + - path-parameters: + id: id + response: + body: + items: + - type: insight + insightId: a3f1c9d2-4b7e-4f8a-9c3d-2e5b7f8a1c2d + systemKey: insight_system_key_01 + position: + x: 2 + 'y': 3 + size: + width: 4 + height: 3 + id: d290f1ee-6c54-4b01-90e6-d701748f0851 + orgId: f47ac10b-58cc-4372-a567-0e02b2c3d479 + createdAt: '2024-01-15T09:30:00Z' + updatedAt: '2024-01-15T09:30:00Z' + systemKey: board_system_key_123 + name: Sales Performance Dashboard + layout: + columns: 6 + timeRangeOverride: + step: hour + start: '-7d' + end: now + timezone: America/New_York + /reporting/board: + post: + x-fern-examples: + - request: + name: Sales Performance Dashboard + layout: + columns: 6 + response: + body: + items: + - type: insight + insightId: insight-9f8b7c6d-1234-4a56-b789-0a1b2c3d4e5f + systemKey: syskey-analytics-001 + position: + x: 0 + 'y': 0 + size: + width: 3 + height: 2 + id: board-7a6b5c4d-9876-4321-0fed-cba987654321 + orgId: org-12345678-abcd-efgh-ijkl-9876543210ab + createdAt: '2024-01-15T09:30:00Z' + updatedAt: '2024-01-15T09:30:00Z' + systemKey: syskey-board-001 + name: Sales Performance Dashboard + layout: + columns: 6 + timeRangeOverride: + step: day + start: '-7d' + end: now + timezone: UTC + get: + x-fern-examples: + - response: + body: + results: + - items: + - type: insight + insightId: a1b2c3d4-e5f6-7890-abcd-ef1234567890 + systemKey: sys-board-insight-001 + position: + x: 0 + 'y': 0 + size: + width: 3 + height: 2 + id: board-1234abcd-5678-ef90-gh12-ijklmnopqrst + orgId: org-9876zyxw-5432-vuts-rqpo-nmlkjihgfedc + createdAt: '2024-01-15T09:30:00Z' + updatedAt: '2024-01-15T09:30:00Z' + systemKey: sys-board-001 + name: Executive Summary Dashboard + layout: + columns: 6 + timeRangeOverride: + step: day + start: '-7d' + end: now + timezone: UTC + metadata: + itemsPerPage: 25 + totalItems: 150 + currentPage: 1 + totalPages: 6 + hasNextPage: true + nextCursor: cursor_abcdef123456 + sortOrder: DESC + itemsBeyondRetention: false + createdAtLe: '2024-01-15T09:30:00Z' + createdAtGe: '2023-12-15T09:30:00Z' + /reporting/board/default/metrics-overview: + get: + x-fern-examples: + - response: + body: + items: + - type: insight + insightId: a1b2c3d4-e5f6-7890-ab12-cd34ef567890 + systemKey: sys_insight_001 + position: + x: 2 + 'y': 3 + size: + width: 4 + height: 3 + id: board_9876543210abcdef + orgId: org_1234567890abcdef + createdAt: '2024-01-15T09:30:00Z' + updatedAt: '2024-04-20T15:45:00Z' + systemKey: sys_board_default_metrics + name: Default Metrics Overview + layout: + columns: 6 + timeRangeOverride: + step: day + start: '-7d' + end: now + timezone: UTC + /observability/scorecard: + post: + x-fern-examples: + - request: + metrics: + - conditions: + - type: comparator + comparator: '=' + value: 1 + points: 10 + - type: comparator + comparator: '>' + value: 5 + points: 20 + - type: comparator + comparator: <= + value: 3 + points: 15 + structuredOutputId: call_duration_seconds + - conditions: + - type: comparator + comparator: '=' + value: 1 + points: 30 + structuredOutputId: agent_satisfaction + - conditions: + - type: comparator + comparator: '=' + value: 0 + points: 5 + structuredOutputId: call_dropped + response: + body: + id: a3f47b9e-8c2d-4f1a-9b7e-2d3f5c6a7b8d + orgId: org_9f8e7d6c5b4a3210 + createdAt: '2024-01-15T09:30:00Z' + updatedAt: '2024-01-15T09:30:00Z' + name: Customer Support Quality Scorecard + description: Scorecard to evaluate call metrics and agent performance for customer support calls. + metrics: + - conditions: + - type: comparator + comparator: '=' + value: 1 + points: 10 + - type: comparator + comparator: '>' + value: 5 + points: 20 + - type: comparator + comparator: <= + value: 3 + points: 15 + structuredOutputId: call_duration_seconds + - conditions: + - type: comparator + comparator: '=' + value: 1 + points: 30 + structuredOutputId: agent_satisfaction + - conditions: + - type: comparator + comparator: '=' + value: 0 + points: 5 + structuredOutputId: call_dropped + assistantIds: + - assistant_12345abcde + - assistant_67890fghij + get: + x-fern-examples: + - response: + body: + results: + - id: a3f1c9d2-4b7e-4f8a-9c3d-2e5b7f1a9c8d + orgId: d9f8e7c6-b5a4-4321-9f8e-7d6c5b4a3f2e + createdAt: '2024-01-15T09:30:00Z' + updatedAt: '2024-01-15T09:30:00Z' + name: Customer Support Quality Scorecard + description: Scorecard evaluating key customer support call metrics for Q1 2024. + metrics: + - conditions: + - type: comparator + comparator: '=' + value: 1 + points: 10 + structuredOutputId: metric-voice-quality-001 + assistantIds: + - assistant-1234abcd + metadata: + itemsPerPage: 10 + totalItems: 45 + currentPage: 1 + totalPages: 5 + hasNextPage: true + nextCursor: eyJjdXJzb3IiOiIyMDI0LTAxLTE1VDA5OjMwOjAwWiJ9 + sortOrder: ASC + itemsBeyondRetention: false + createdAtLe: '2024-01-15T09:30:00Z' + createdAtGe: '2023-12-01T00:00:00Z' diff --git a/fern/assistants/examples/multilingual-agent.mdx b/fern/assistants/examples/multilingual-agent.mdx index dae370197..a85e6fe15 100644 --- a/fern/assistants/examples/multilingual-agent.mdx +++ b/fern/assistants/examples/multilingual-agent.mdx @@ -298,8 +298,8 @@ We will be creating a dynamic multilingual customer support agent for GlobalTech // Option 2: Google Multilingual const googleTranscriber = { provider: "google", - model: "latest", - language: "multilingual" + model: "gemini-2.0-flash", + language: "Multilingual" }; // Update assistant with transcriber @@ -320,8 +320,8 @@ We will be creating a dynamic multilingual customer support agent for GlobalTech # Option 2: Google Multilingual google_transcriber = { "provider": "google", - "model": "latest", - "language": "multilingual" + "model": "gemini-2.0-flash", + "language": "Multilingual" } # Update assistant with transcriber @@ -356,8 +356,8 @@ We will be creating a dynamic multilingual customer support agent for GlobalTech -d '{ "transcriber": { "provider": "google", - "model": "latest", - "language": "multilingual" + "model": "gemini-2.0-flash", + "language": "Multilingual" } }' ``` @@ -371,49 +371,24 @@ We will be creating a dynamic multilingual customer support agent for GlobalTech ## 4. Configure Multilingual Voice Synthesis - + - 1. In the **Voice** section of your assistant: - 2. **Provider**: Select `Azure` (best multilingual coverage) - 3. **Voice**: Choose primary voice `en-US-AriaNeural` (English) - 4. **Add fallback voices**: - - Spanish: `es-ES-ElviraNeural` (Spain) or `es-MX-DaliaNeural` (Mexico) - - French: `fr-FR-DeniseNeural` (France) or `fr-CA-SylvieNeural` (Canada) - 5. **Alternative providers**: ElevenLabs, OpenAI, or PlayHT all support multiple languages + 1. In the **Voice** section of your assistant, select **Vapi**. + 2. Choose a Vapi Voice. + 3. Set **Version** to `2`. + 4. Leave the language unset, or set it to `auto`. + + Voice fallbacks activate when synthesis fails. They do not select a different voice based on the detected language. ```typescript - // Multi-language voice configuration + // Vapi Voices V2 automatically selects the synthesis language. const multilingualVoice = { - provider: "azure", - voiceId: "en-US-AriaNeural", // Primary English voice - fallbackPlan: { - voices: [ - { - provider: "azure", - voiceId: "es-ES-ElviraNeural" // Spanish (Spain) - }, - { - provider: "azure", - voiceId: "fr-FR-DeniseNeural" // French (France) - }, - { - provider: "azure", - voiceId: "es-MX-DaliaNeural" // Spanish (Mexico) - }, - { - provider: "azure", - voiceId: "fr-CA-SylvieNeural" // French (Canada) - } - ] - } - }; - - // Alternative: ElevenLabs multilingual - const elevenLabsVoice = { - provider: "11labs", - voiceId: "multilingual-v2" // Supports multiple languages + provider: "vapi", + voiceId: "Elliot", + version: 2, + language: "auto" }; await vapi.assistants.update("YOUR_ASSISTANT_ID", { @@ -423,30 +398,12 @@ We will be creating a dynamic multilingual customer support agent for GlobalTech ```python - # Multi-language voice configuration + # Vapi Voices V2 automatically selects the synthesis language. multilingual_voice = { - "provider": "azure", - "voiceId": "en-US-AriaNeural", # Primary English voice - "fallbackPlan": { - "voices": [ - { - "provider": "azure", - "voiceId": "es-ES-ElviraNeural" # Spanish (Spain) - }, - { - "provider": "azure", - "voiceId": "fr-FR-DeniseNeural" # French (France) - }, - { - "provider": "azure", - "voiceId": "es-MX-DaliaNeural" # Spanish (Mexico) - }, - { - "provider": "azure", - "voiceId": "fr-CA-SylvieNeural" # French (Canada) - } - ] - } + "provider": "vapi", + "voiceId": "Elliot", + "version": 2, + "language": "auto" } # Update assistant with voice configuration @@ -467,20 +424,10 @@ We will be creating a dynamic multilingual customer support agent for GlobalTech -H "Content-Type: application/json" \ -d '{ "voice": { - "provider": "azure", - "voiceId": "en-US-AriaNeural", - "fallbackPlan": { - "voices": [ - { - "provider": "azure", - "voiceId": "es-ES-ElviraNeural" - }, - { - "provider": "azure", - "voiceId": "fr-FR-DeniseNeural" - } - ] - } + "provider": "vapi", + "voiceId": "Elliot", + "version": 2, + "language": "auto" } }' ``` @@ -1084,25 +1031,13 @@ Keep responses concise (under 50 words) while being thorough and helpful.""" ## Alternative: Squad-Based Language Selection -For a more structured approach with explicit language selection, see our comprehensive [Squad-based multilingual support](../../squads/examples/multilingual-support) guide. This approach lets customers choose their language at the start of the call, then routes them to dedicated conversation paths optimized for each language. +For a more structured approach with explicit language selection, see our comprehensive [Squad-based multilingual support](/squads/examples/multilingual-support) guide. This approach lets customers choose their language at the start of the call, then routes them to dedicated conversation paths optimized for each language. ## Provider Support Summary -**Speech-to-Text (Transcription):** -- **Gladia**: Solaria, automatic language detection and code-switching. -- **Deepgram**: Nova 2, Nova 3 with "Multi" language setting -- **Google**: Latest models with "Multilingual" language setting -- **All other providers**: Single language only, no automatic detection - -**Text-to-Speech (Voice Synthesis):** -- **Azure**: 400+ voices across 140+ languages (recommended for coverage) -- **ElevenLabs**: 30+ languages with premium quality -- **OpenAI**: 50+ languages with consistent quality -- **PlayHT**: 80+ languages, cost-effective -- **All providers**: Support multiple languages natively +Automatic detection and code-switching require provider-specific transcriber settings. Review [Multilingual support](/customization/multilingual) and the individual [transcriber provider pages](/providers/transcriber/overview) for current configurations. -**Language Models:** -- **All major LLMs** (GPT-4o, Claude, Gemini, Llama, etc.): Native multilingual support +For speech synthesis, confirm that the selected model and voice support every language in your assistant's system prompt. Vapi Voices V2 can select the synthesis language automatically. Other providers may require a provider-specific model, voice, or language setting. ## Next Steps @@ -1110,9 +1045,9 @@ Just like that, you've built a dynamic multilingual customer support agent that Consider reading the following guides to further enhance your multilingual implementation: -* [**Squad-based Multilingual Support**](../../squads/examples/multilingual-support) - Compare with structured language selection approach -* [**Multilingual Configuration Guide**](../../../customization/multilingual) - Learn about all multilingual configuration options -* [**Custom Tools**](../../../tools/custom-tools) - Build advanced multilingual tools and integrations +* [**Squad-based Multilingual Support**](/squads/examples/multilingual-support) - Compare with structured language selection approach +* [**Multilingual Configuration Guide**](/customization/multilingual) - Learn about all multilingual configuration options +* [**Custom Tools**](/tools/custom-tools) - Build advanced multilingual tools and integrations Need help with multilingual implementation? Chat with the team on our [Discord](https://discord.com/invite/pUFNcf2WmH) or mention us on [X/Twitter](https://x.com/Vapi_AI). diff --git a/fern/customization/multilingual.mdx b/fern/customization/multilingual.mdx index ccd910194..fe4dc192f 100644 --- a/fern/customization/multilingual.mdx +++ b/fern/customization/multilingual.mdx @@ -29,7 +29,7 @@ Set up your transcriber to automatically detect and process multiple languages. 2. Create a new assistant or edit an existing one 3. In the **Transcriber** section: - **Provider**: Select `Deepgram` (recommended), `Google`, or `Gladia` - - **Model**: For Deepgram, choose `Nova 2` or `Nova 3`; for Google, choose `Latest`; for Gladia, choose `Solaria` + - **Model**: For Deepgram, choose `Nova 2` or `Nova 3`; for Google, choose `Gemini 2.0 Flash`; for Gladia, choose `Solaria` - **Language / Mode**: Set `Multi` (Deepgram), `Multilingual` (Google), or choose the language you want to transcribe (Gladia) 4. **Other providers**: May require a single languages and not auto-detect 5. Click **Save** to apply the configuration @@ -53,8 +53,8 @@ Set up your transcriber to automatically detect and process multiple languages. // Alternative: Google for multilingual support const googleMultilingual = { provider: "google", - model: "latest", - language: "multilingual" + model: "gemini-2.0-flash", + language: "Multilingual" }; ``` @@ -78,8 +78,8 @@ Set up your transcriber to automatically detect and process multiple languages. # Alternative: Google for multilingual support google_multilingual = { "provider": "google", - "model": "latest", - "language": "multilingual" + "model": "gemini-2.0-flash", + "language": "Multilingual" } ``` @@ -105,8 +105,8 @@ Set up your transcriber to automatically detect and process multiple languages. -d '{ "transcriber": { "provider": "google", - "model": "latest", - "language": "multilingual" + "model": "gemini-2.0-flash", + "language": "Multilingual" } }' ``` @@ -198,6 +198,21 @@ Configure your assistant to use appropriate voices for each detected language. + +Vapi Voices V2 can select the synthesis language automatically. Set `voice.provider` to `vapi`, `voice.version` to `2`, and `voice.language` to `auto`: + +```json +{ + "voice": { + "provider": "vapi", + "voiceId": "Elliot", + "version": 2, + "language": "auto" + } +} +``` + + **Voice Provider Support:** Unlike transcription, all major voice providers (Azure, ElevenLabs, OpenAI, etc.) support multiple languages. Azure offers the most comprehensive coverage with 400+ voices across 140+ languages. @@ -517,7 +532,7 @@ Validate your configuration with different languages and scenarios. Now that you have multilingual support configured: -- **[Build a complete multilingual agent](../assistants/examples/multilingual-agent):** Follow our step-by-step implementation guide -- **[Custom voices](custom-voices/custom-voice):** Set up region-specific custom voices -- **[System prompting](../prompting-guide):** Design effective multilingual prompts -- **[Call analysis](../call-analysis):** Monitor language performance and usage +- **[Build a complete multilingual agent](/assistants/examples/multilingual-agent):** Follow our step-by-step implementation guide +- **[Custom voices](/customization/custom-voices/custom-voice):** Set up region-specific custom voices +- **[System prompting](/prompting-guide):** Design effective multilingual prompts +- **[Call analysis](/assistants/call-analysis):** Monitor language performance and usage diff --git a/fern/customization/provider-keys.mdx b/fern/customization/provider-keys.mdx index 4c98084ae..a19ffa68d 100644 --- a/fern/customization/provider-keys.mdx +++ b/fern/customization/provider-keys.mdx @@ -1,6 +1,7 @@ --- title: Provider Keys subtitle: Bring your own API keys to Vapi. +description: Connect provider credentials in Vapi and find configuration details for transcriber, model, voice, and cloud providers. slug: customization/provider-keys --- @@ -11,19 +12,17 @@ No problem! You can bring your own API keys to Vapi. You can add them in the [Da ## Transcription Providers -Currently, the only available transcription provider is `deepgram`. To use a custom model, you can specify the deepgram model ID in the `transcriber.model` parameter of the [Assistant](/api-reference/assistants/create-assistant). +Choose the provider and its supported options in the assistant's `transcriber` configuration. See [Transcriber providers](/providers/transcriber/overview) and the [`transcriber` configuration](/api-reference/assistants/create#request.body.transcriber) in the API reference. ## Model Providers -We are currently have support for any OpenAI-compatible endpoint. This includes services like [OpenRouter](https://openrouter.ai/), [AnyScale](https://www.anyscale.com/), [Together AI](https://www.together.ai/), or your own server. +Choose the provider and model in the assistant's `model` configuration. See [Model providers](/providers/model/overview) and the [`model` configuration](/api-reference/assistants/create#request.body.model) in the API reference. -To use one of these providers, you can specify the `provider` and `model` in the `model` parameter of the [Assistant](/api-reference/assistants/create-assistant). - -You can find more details in the [Custom LLMs](/customization/custom-llm/fine-tuned-openai-models) section of the documentation. +For an OpenAI-compatible endpoint that is not represented by a native provider, see [Custom LLMs](/customization/custom-llm/using-your-server). ## Voice Providers -All voice providers are supported. Once you've validated your API through the [Dashboard](https://dashboard.vapi.ai), any voice ID from your provider can be used in the `voice.voiceId` field of the [Assistant](/api-reference/assistants/create-assistant). +Choose the provider, voice ID, and supported options in the assistant's `voice` configuration. See [Voice providers](/providers/voice/overview) and the [`voice` configuration](/api-reference/assistants/create#request.body.voice) in the API reference. ## Cloud Providers @@ -33,6 +32,6 @@ Cloudflare R2. You can find more details on how to configure your Cloud Provider keys here: - * [AWS S3](/providers/cloud/s3) - * [GCP Cloud Storage](/providers/cloud/gcp) - * [Cloudflare R2](/providers/cloud/cloudflare) +- [AWS S3](/providers/cloud/s3) +- [Google Cloud Storage](/providers/cloud/gcp) +- [Cloudflare R2](/providers/cloud/cloudflare) diff --git a/fern/customization/speech-configuration.mdx b/fern/customization/speech-configuration.mdx index 198c233d7..3f8f4c8e7 100644 --- a/fern/customization/speech-configuration.mdx +++ b/fern/customization/speech-configuration.mdx @@ -49,7 +49,7 @@ This plan defines the parameters for when the assistant begins speaking after th **Audio-text based providers:** - - **Deepgram Flux**: Deepgram's latest transcriber model with built-in conversational speech recognition. Flux combines high-quality speech-to-text with native turn detection, while delivering ultra-low latency and Nova-3 level accuracy. Available in English (`flux-general-en`) and multilingual (`flux-general-multi`) variants. Supported languages for `flux-general-multi`: English (`en`), Spanish (`es`), French (`fr`), German (`de`), Hindi (`hi`), Russian (`ru`), Portuguese (`pt`), Japanese (`ja`), Italian (`it`), Dutch (`nl`). + - **Deepgram Flux**: Deepgram's latest transcriber model with built-in conversational speech recognition. Flux combines high-quality speech-to-text with native turn detection, while delivering ultra-low latency and Nova-3 level accuracy. Available in English (`flux-general-en`) and multilingual (`flux-general-multi`) variants. See [Deepgram's supported languages](/providers/transcriber/deepgram#supported-languages) for the current model and language combinations. - **Assembly**: Transcriber that also reports end-of-turn detection. To use Assembly, choose it as your transcriber without setting a separate smart endpointing plan. As transcripts arrive, we consider the `end_of_turn` flag that Assembly sends to mark the end-of-turn, stream to the LLM, and generate a response. diff --git a/fern/customization/transcriber-fallback-plan.mdx b/fern/customization/transcriber-fallback-plan.mdx index afa019ea8..28ec3311a 100644 --- a/fern/customization/transcriber-fallback-plan.mdx +++ b/fern/customization/transcriber-fallback-plan.mdx @@ -81,7 +81,7 @@ Manual fallbacks give you full control over which providers Vapi tries, and in w - If HIPAA compliance is enabled on your account or assistant, only [HIPAA-compliant transcribers](/security-and-privacy/hipaa#hipaa-compliant-providers) **Deepgram**, **Azure**, and **Soniox**, will be available as fallback options. + If HIPAA compliance is enabled, choose every fallback from the current list of [HIPAA-compliant transcription providers](/security-and-privacy/hipaa#transcription-providers-stt). ### Configure via API @@ -118,80 +118,123 @@ In this example, if Deepgram fails, Vapi tries AssemblyAI first, then Azure. If ## Provider-specific settings -Each transcriber provider supports different configuration options. Expand the accordion below to see available settings for each provider. +Each transcriber provider supports different configuration options. Expand a provider below to review its available settings. For the complete schema, see the provider-specific transcriber fields in the [Create Assistant API reference](/api-reference/assistants/create#request.body.transcriber). + + - **language**: Language code (`multi` for multilingual or `en` for English). + - **speechModel**: AssemblyAI streaming speech model. + - **mode**: Accuracy and latency mode for `universal-3-5-pro`: `max_accuracy`, `min_latency`, or `balanced`. + - **prompt**: Additional context for `universal-3-5-pro`, up to 1,750 characters. + - **agentContext**: Voice-agent context for `universal-3-5-pro`, up to 1,750 characters. + - **languageCodes**: Language hints for `universal-3-5-pro` automatic language detection. + - **realtimeUrl**: WebSocket URL used for the realtime transcription connection. + - **wordBoost**: Custom vocabulary array, up to 2,500 characters per entry. + - **keytermsPrompt**: Up to 100 keyterms, with a maximum of 50 characters each. + - **endUtteranceSilenceThreshold**: Duration of silence in milliseconds used to detect the end of an utterance. + - **disablePartialTranscripts**: Set to `true` to disable partial transcripts. + - **confidenceThreshold**: Minimum confidence for accepting transcripts, from `0` to `1`. + - **formatTurns**: Enables transcript formatting. + - **endOfTurnConfidenceThreshold**: Minimum end-of-turn confidence, from `0` to `1`. + - **minEndOfTurnSilenceWhenConfident**: Minimum silence in milliseconds before ending a confident turn. + - **maxTurnSilence**: Maximum turn silence in milliseconds. + - **vadAssistedEndpointingEnabled**: Enables VAD-assisted endpoint detection. + + + - **language**: Language code in BCP 47 format, such as `en-US`, `es-MX`, or `fr-FR`. + - **segmentationSilenceTimeoutMs**: Duration of silence after which a phrase is finalized, from `100` to `5000` milliseconds. + - **segmentationMaximumTimeMs**: Maximum segment duration, from `20000` to `70000` milliseconds. + - **segmentationStrategy**: Phrase-boundary strategy: `Default`, `Time`, or `Semantic`. + + + - **model**: Cartesia transcription model. + - **language**: Language code. Language availability depends on the selected model. + - - **model**: Model selection (`nova-3`, `nova-3-general`, `nova-3-medical`, `nova-2`, `flux-general-en`, `flux-general-multi`, etc.). Use `flux-general-en` for English-only conversations and `flux-general-multi` for multilingual conversations. Supported languages for `flux-general-multi`: `en`, `es`, `fr`, `de`, `hi`, `ru`, `pt`, `ja`, `it`, `nl`. + - **model**: Deepgram transcription model. - **language**: Language code for transcription. - - **keywords**: Keywords with optional boost values for improved recognition (e.g., `["companyname", "productname:2"]`). - - **keyterm**: Keyterm prompting for up to 90% keyword recall rate improvement. - - **smartFormat** (boolean): Enable smart formatting for numbers and dates. - - **eotThreshold** (0.5-0.9): End-of-turn confidence threshold. Only available with Flux models. - - **eotTimeoutMs** (500-10000): Maximum time to wait after speech before finalizing turn. Only available with Flux models. Default is 5000ms. + - **languages**: Language hints for Flux Multilingual. Omit this field to allow automatic detection. + - **keywords**: Keywords with optional boost values, such as `["companyname", "productname:2"]`. + - **keyterm**: Important words or phrases for keyterm prompting. + - **smartFormat**: Enables formatting for values such as numbers and dates. + - **endpointing**: Silence duration used for endpointing, from `10` to `500` milliseconds. + - **mipOptOut**: Opts your account out of Deepgram's Model Improvement Partnership when you use your own Deepgram API key. + - **numerals**: Converts spoken numbers to numerals. + - **profanityFilter**: Replaces profanity in transcripts with asterisks. + - **redaction**: Redacts selected categories: `pci`, `pii`, `phi`, or `numbers`. + - **confidenceThreshold**: Minimum confidence for accepting transcripts, from `0` to `1`. + - **eotThreshold**: End-of-turn confidence threshold for Flux models, from `0.5` to `0.9`. + - **eotTimeoutMs**: Maximum wait after speech before finalizing a turn with Flux, from `500` to `10000` milliseconds. + + See [Deepgram](/providers/transcriber/deepgram) for current models and model-specific language support. - - - **language**: Language code (`multi` for multilingual, `en` for English). - - **speechModel**: Streaming speech model (`universal-streaming-english` or `universal-streaming-multilingual`). - - **wordBoost**: Custom vocabulary array (up to 2500 characters total). - - **keytermsPrompt**: Array of keyterms for improved recognition (up to 100 terms, 50 characters each). Costs additional $0.04/hour. - - **endUtteranceSilenceThreshold**: Duration of silence in milliseconds to detect end of utterance. - - **disablePartialTranscripts** (boolean): Set to `true` to disable partial transcripts. - - **confidenceThreshold** (0-1): Minimum confidence threshold for accepting transcriptions. Default is 0.4. - - **vadAssistedEndpointingEnabled** (boolean): Enable VAD-based endpoint detection. - - - - **language**: Language code in BCP-47 format (e.g., `en-US`, `es-MX`, `fr-FR`). - - **segmentationSilenceTimeoutMs** (100-5000): Duration of silence after which a phrase is finalized. Configure to adjust sensitivity to pauses. - - **segmentationMaximumTimeMs** (20000-70000): Maximum duration a segment can reach before being cut off. - - **segmentationStrategy**: Controls phrase boundary detection. Options: `Default`, `Time`, or `Semantic`. + + - **model**: ElevenLabs transcription model. + - **language**: ISO 639-1 language code. + - **silenceThresholdSeconds**: Silence before VAD commits, from `0.3` to `3` seconds. + - **confidenceThreshold**: VAD sensitivity, from `0.1` to `0.9`; lower values are more sensitive. + - **minSpeechDurationMs**: Minimum speech duration for VAD, from `50` to `2000` milliseconds. + - **minSilenceDurationMs**: Minimum silence duration for VAD, from `50` to `2000` milliseconds. - - **model**: Model selection (`fast`, `accurate`, or `solaria-1`). + - **model**: Gladia transcription model. + - **languageBehaviour**: Controls automatic or manual language detection. - **language**: Language code. - - **confidenceThreshold** (0-1): Minimum confidence for transcription acceptance. Default is 0.4. - - **endpointing** (0.01-10): Time in seconds to wait before considering speech ended. - - **speechThreshold** (0-1): Speech detection sensitivity (0.0 to 1.0). - - **prosody** (boolean): Enable prosody detection (laugh, giggle, music, etc.). - - **audioEnhancer** (boolean): Pre-process audio for improved accuracy (increases latency). - - **transcriptionHint**: Hint text to guide transcription. - - **customVocabularyEnabled** (boolean): Enable custom vocabulary. - - **customVocabularyConfig**: Custom vocabulary configuration with vocabulary array and default intensity. - - **region**: Processing region (`us-west` or `eu-west`). - - **receivePartialTranscripts** (boolean): Enable partial transcript delivery. - - - - **model**: Model selection (currently only `default`). - - **language**: Language code. - - **operatingPoint**: Accuracy level. `standard` for faster turnaround, `enhanced` for highest accuracy. Default is `enhanced`. - - **region**: Processing region (`eu` for Europe, `us` for United States). Default is `eu`. - - **enableDiarization** (boolean): Enable speaker identification for multi-speaker conversations. - - **maxDelayMs**: Maximum delay in milliseconds for partial transcripts. Balances latency and accuracy. - - - See [Configure Soniox](/providers/transcriber/soniox) for setup instructions. - - - **model**: Model selection (currently only `stt-rt-v5` for new configurations). - - **language**: ISO 639-1 language code. Soniox supports multilingual transcription with a single universal model. - - **languageHintsStrict** (boolean): Restrict transcription to the selected language when enabled. When disabled, Soniox can automatically detect and transcribe supported languages. Default is `true`. - - **maxEndpointDelayMs** (500-3000): Maximum delay in milliseconds between the end of speech and endpoint detection. Lower values provide faster turn-taking but may increase false endpoints. Default is `500`. - - **customVocabulary**: Array of brand names, product names, or other domain-specific terms to improve recognition accuracy. + - **languages**: Language codes used when manual multilingual detection is configured. + - **confidenceThreshold**: Minimum confidence for accepting transcripts, from `0` to `1`. + - **endpointing**: Time to wait before considering speech complete, from `0.01` to `10` seconds. + - **speechThreshold**: Speech-detection sensitivity, from `0` to `1`. + - **prosody**: Enables detection of non-speech events such as laughter and music. + - **audioEnhancer**: Preprocesses audio to improve accuracy, with additional latency. + - **transcriptionHint**: Context that guides transcription, up to 600 characters. + - **customVocabularyEnabled**: Enables custom vocabulary. + - **customVocabularyConfig**: Custom vocabulary and intensity configuration. + - **region**: Processing region, `us-west` or `eu-west`. + - **receivePartialTranscripts**: Enables partial transcripts. - - **model**: Gemini model selection. - - **language**: Language selection (e.g., `Multilingual`, `English`, `Spanish`, `French`). + - **model**: Gemini transcription model. + - **language**: Language selection, such as `Multilingual`, `English`, `Spanish`, or `French`. - - **model**: OpenAI Realtime STT model selection (required). + - **model**: OpenAI realtime transcription model. - **language**: Language code for transcription. - - - **model**: Model selection (currently only `scribe_v1`). + + - **model**: Soniox transcription model. - **language**: ISO 639-1 language code. + - **languages**: Expected-language hints. An empty array enables automatic detection without hints. + - **languageHintsStrict**: Restricts transcription to selected language hints when enabled. + - **maxEndpointDelayMs**: Maximum endpoint delay, from `500` to `3000` milliseconds. + - **customVocabulary**: Brand names, product names, or other domain-specific terms. + - **contextGeneral**: Key-value pairs that provide domain or topic context. + + See [Soniox](/providers/transcriber/soniox) for current model and language details. - - - **model**: Model selection (currently only `ink-whisper`). - - **language**: ISO 639-1 language code. + + - **model**: Speechmatics transcription model. + - **language**: Language code or `auto` for automatic detection. + - **operatingPoint**: `standard` for faster transcription or `enhanced` for higher accuracy. Defaults to `enhanced`. + - **region**: Processing region, `eu` or `us`. Defaults to `eu`. + - **enableDiarization**: Enables speaker identification for multi-speaker conversations. + - **maxDelay**: Maximum delay for partial transcripts, from `500` to `10000` milliseconds. Defaults to `3000`. + - **customVocabulary**: Words or phrases to improve recognition, with optional `soundsLike` variations. + - **numeralStyle**: Number formatting style: `written` or `spoken`. Defaults to `written`. + - **endOfTurnSensitivity**: End-of-turn sensitivity, from `0` to `1`. Defaults to `0.5`. + - **removeDisfluencies**: Removes disfluencies from English transcripts when enabled. + - **minimumSpeechDuration**: Minimum speech-segment duration, from `0` to `5` seconds. + + + - **model**: Talkscriber transcription model. + - **language**: Language code for transcription. + + See [Talkscriber](/providers/transcriber/talkscriber) for the supported model and languages. + + + - **model**: xAI transcription model. + - **language**: Language code for transcription. + + See [xAI](/providers/transcriber/xai) for the supported model and languages. @@ -202,7 +245,7 @@ Each transcriber provider supports different configuration options. Expand the a - **Combine both** for maximum reliability—manual fallbacks run first, auto fallback catches anything they miss. - Use **different providers** for manual fallbacks to protect against provider-wide outages. - Consider **language compatibility** when selecting fallbacks—ensure all fallback transcribers support your required languages. -- For **HIPAA compliance**, ensure all fallbacks are [compliant providers](/security-and-privacy/hipaa#hipaa-compliant-providers) (Deepgram, Azure, or Soniox) and review data routing implications before enabling auto fallback. +- For **HIPAA compliance**, choose every fallback from the current list of [HIPAA-compliant transcription providers](/security-and-privacy/hipaa#transcription-providers-stt) and review data-routing implications before enabling auto fallback. ## FAQ @@ -211,7 +254,7 @@ Each transcriber provider supports different configuration options. Expand the a Auto fallback lets Vapi intelligently select an alternative provider for you—no configuration needed. Manual fallback lets you specify exact providers in a specific priority order. You can use both together: manual fallbacks are tried first, and auto fallback acts as a safety net if they all fail. - All major transcriber providers are supported: Deepgram, AssemblyAI, Azure, Gladia, Google, Speechmatics, Soniox, Cartesia, ElevenLabs, and OpenAI. + Review [Transcriber providers](/providers/transcriber/overview) for the current provider list and the [`fallbackPlan.transcribers` schema](/api-reference/assistants/create#request.body.transcriber) for accepted fallback configurations. No additional fees for using fallback transcribers. You are only billed for the transcriber that processes the audio. diff --git a/fern/customization/voice-pipeline-configuration.mdx b/fern/customization/voice-pipeline-configuration.mdx index c7cfbe5c9..bd2c85f26 100644 --- a/fern/customization/voice-pipeline-configuration.mdx +++ b/fern/customization/voice-pipeline-configuration.mdx @@ -281,7 +281,7 @@ Deepgram Flux's end-of-turn detection is configured at the transcriber level, al } ``` - Supported languages: English (`en`), Spanish (`es`), French (`fr`), German (`de`), Hindi (`hi`), Russian (`ru`), Portuguese (`pt`), Japanese (`ja`), Italian (`it`), Dutch (`nl`). Set the `language` field to one of these codes, or omit it to enable automatic language detection. + Omit `languages` to enable automatic language detection, or set it to an array of expected language codes to provide hints. See [Deepgram's supported languages](/providers/transcriber/deepgram#supported-languages) for the current Flux language list. @@ -773,7 +773,7 @@ User Interrupts → Assistant Audio Stopped → backoffSeconds Blocks All Output } ``` - **Optimized for:** Multilingual conversations where Deepgram is set as transcriber. Supported languages: English (`en`), Spanish (`es`), French (`fr`), German (`de`), Hindi (`hi`), Russian (`ru`), Portuguese (`pt`), Japanese (`ja`), Italian (`it`), Dutch (`nl`). Omit `language` to enable automatic language detection. + **Optimized for:** Multilingual conversations where Deepgram is set as transcriber. Omit `languages` to enable automatic language detection, or set it to an array of expected language codes to provide hints. See [Deepgram's supported languages](/providers/transcriber/deepgram#supported-languages) for the current Flux language list. diff --git a/fern/docs.yml b/fern/docs.yml index 22a107e26..134a6c9fc 100644 --- a/fern/docs.yml +++ b/fern/docs.yml @@ -636,50 +636,34 @@ navigation: collapsed: true icon: fa-light fa-link contents: - - section: Voices (Text-to-speech) - path: providers/voice/overview.mdx - icon: fa-light fa-waveform-lines + - section: Transcribers (Speech-to-text) + path: providers/transcriber/overview.mdx + icon: fa-light fa-microphone contents: - - section: Vapi Voices - path: providers/voice/vapi-voices.mdx - contents: - - page: Legacy migration - path: providers/voice/vapi-voices/legacy-migration.mdx - icon: fa-light fa-triangle-exclamation + - page: AssemblyAI + path: providers/transcriber/assembly-ai.mdx - page: Azure - path: providers/voice/azure.mdx + path: providers/transcriber/azure.mdx - page: Cartesia - path: providers/voice/cartesia.mdx + path: providers/transcriber/cartesia.mdx - page: Deepgram - path: providers/voice/deepgram.mdx + path: providers/transcriber/deepgram.mdx - page: ElevenLabs - path: providers/voice/elevenlabs.mdx - - page: Hume - path: providers/voice/hume.mdx - - page: Inworld - path: providers/voice/inworld.mdx - - page: LMNT - path: providers/voice/imnt.mdx - - page: Microsoft - path: providers/voice/microsoft.mdx - - page: MiniMax - path: providers/voice/minimax.mdx - - page: Neuphonic - path: providers/voice/neuphonic.mdx + path: providers/transcriber/elevenlabs.mdx + - page: Gladia + path: providers/transcriber/gladia.mdx + - page: Google + path: providers/transcriber/google.mdx - page: OpenAI - path: providers/voice/openai.mdx - - page: PlayHT - path: providers/voice/playht.mdx - - page: RimeAI - path: providers/voice/rimeai.mdx - - page: Sesame - path: providers/voice/sesame.mdx - - page: Smallest AI - path: providers/voice/smallest-ai.mdx - - page: WellSaid - path: providers/voice/wellsaid.mdx + path: providers/transcriber/openai.mdx + - page: Soniox + path: providers/transcriber/soniox.mdx + - page: Speechmatics + path: providers/transcriber/speechmatics.mdx + - page: Talkscriber + path: providers/transcriber/talkscriber.mdx - page: xAI - path: providers/voice/xai.mdx + path: providers/transcriber/xai.mdx - section: Large language models path: providers/model/overview.mdx @@ -720,34 +704,50 @@ navigation: - page: xAI path: providers/model/xai.mdx - - section: Transcribers (Speech-to-text) - path: providers/transcriber/overview.mdx - icon: fa-light fa-microphone + - section: Voices (Text-to-speech) + path: providers/voice/overview.mdx + icon: fa-light fa-waveform-lines contents: - - page: AssemblyAI - path: providers/transcriber/assembly-ai.mdx + - section: Vapi Voices + path: providers/voice/vapi-voices.mdx + contents: + - page: Legacy migration + path: providers/voice/vapi-voices/legacy-migration.mdx + icon: fa-light fa-triangle-exclamation - page: Azure - path: providers/transcriber/azure.mdx + path: providers/voice/azure.mdx - page: Cartesia - path: providers/transcriber/cartesia.mdx + path: providers/voice/cartesia.mdx - page: Deepgram - path: providers/transcriber/deepgram.mdx + path: providers/voice/deepgram.mdx - page: ElevenLabs - path: providers/transcriber/elevenlabs.mdx - - page: Gladia - path: providers/transcriber/gladia.mdx - - page: Google - path: providers/transcriber/google.mdx + path: providers/voice/elevenlabs.mdx + - page: Hume + path: providers/voice/hume.mdx + - page: Inworld + path: providers/voice/inworld.mdx + - page: LMNT + path: providers/voice/imnt.mdx + - page: Microsoft + path: providers/voice/microsoft.mdx + - page: MiniMax + path: providers/voice/minimax.mdx + - page: Neuphonic + path: providers/voice/neuphonic.mdx - page: OpenAI - path: providers/transcriber/openai.mdx - - page: Soniox - path: providers/transcriber/soniox.mdx - - page: Speechmatics - path: providers/transcriber/speechmatics.mdx - - page: Talkscriber - path: providers/transcriber/talkscriber.mdx + path: providers/voice/openai.mdx + - page: PlayHT + path: providers/voice/playht.mdx + - page: RimeAI + path: providers/voice/rimeai.mdx + - page: Sesame + path: providers/voice/sesame.mdx + - page: Smallest AI + path: providers/voice/smallest-ai.mdx + - page: WellSaid + path: providers/voice/wellsaid.mdx - page: xAI - path: providers/transcriber/xai.mdx + path: providers/voice/xai.mdx - section: Cloud storage icon: fa-light fa-cloud-arrow-up diff --git a/fern/providers/model/cerebras.mdx b/fern/providers/model/cerebras.mdx index 674e5d242..f926c09f2 100644 --- a/fern/providers/model/cerebras.mdx +++ b/fern/providers/model/cerebras.mdx @@ -1,22 +1,46 @@ --- title: Cerebras -subtitle: Connect your Cerebras account to Vapi. -description: Connect Cerebras credentials to Vapi for use with supported integrations. +subtitle: Connect your Cerebras account to use Cerebras models in Vapi. +description: Connect a Cerebras API key to Vapi and configure an assistant with a supported Cerebras model. slug: providers/model/cerebras --- -Cerebras is a large language model provider that runs open models with very fast inference. +Cerebras is a large language model provider that runs open models with very fast inference. Connect your own Cerebras account to use its models on a Vapi assistant. ## What is Cerebras Cerebras serves open large language models on its own inference hardware, optimized for low latency. -Connect your Cerebras account in [Integrations](/providers/integrations). Vapi does not currently list a Cerebras model for new assistant configurations. +## Connect Cerebras + +Cerebras requires your own account. Connect your Cerebras API key on the [Integrations](/providers/integrations) page before configuring an assistant. Without a connected Cerebras key, the models below will not work. + +## Language model + +Set `model.provider` to `cerebras` and `model.model` to a supported model. + +```bash +curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \ + -H "Authorization: Bearer $VAPI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "model": { "provider": "cerebras", "model": "llama3.1-8b" } + }' +``` + +For additional API configuration options, review the [`CerebrasModel` fields](/api-reference/assistants/create#request.body.model.CerebrasModel) in the Create Assistant API reference. + +| Model | Model ID | +| --- | --- | +| Llama 3.1 8B | `llama3.1-8b` | ## Related - + - Connect and manage provider credentials. + Connect your Cerebras API key. + + + Compare every language model provider Vapi supports. diff --git a/fern/providers/model/deepseek.mdx b/fern/providers/model/deepseek.mdx index 84351a515..dd428c2c4 100644 --- a/fern/providers/model/deepseek.mdx +++ b/fern/providers/model/deepseek.mdx @@ -1,22 +1,47 @@ --- title: DeepSeek -subtitle: Connect your DeepSeek account to Vapi. -description: Connect DeepSeek credentials to Vapi for use with supported integrations. +subtitle: Connect your DeepSeek account to use DeepSeek models in Vapi. +description: Connect a DeepSeek API key to Vapi and configure an assistant with a supported DeepSeek model. slug: providers/model/deepseek --- -DeepSeek is a large language model provider focused on chat and reasoning models. +DeepSeek is a large language model provider focused on chat and reasoning models. Connect your own DeepSeek account to use its models on a Vapi assistant. ## What is DeepSeek DeepSeek builds large language models for chat and reasoning use cases. -Connect your DeepSeek account in [Integrations](/providers/integrations). Vapi does not currently list a DeepSeek model for new assistant configurations. +## Connect DeepSeek + +DeepSeek requires your own account. Connect your DeepSeek API key on the [Integrations](/providers/integrations) page before configuring an assistant. Without a connected DeepSeek key, the models below will not work. + +## Language model + +Set `model.provider` to `deep-seek` and `model.model` to a supported model. + +```bash +curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \ + -H "Authorization: Bearer $VAPI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "model": { "provider": "deep-seek", "model": "deepseek-chat" } + }' +``` + +For additional API configuration options, review the [`DeepSeekModel` fields](/api-reference/assistants/create#request.body.model.DeepSeekModel) in the Create Assistant API reference. + +| Model | Model ID | +| --- | --- | +| DeepSeek-V3 | `deepseek-chat` | +| DeepSeek-R1 | `deepseek-reasoner` | ## Related - + - Connect and manage provider credentials. + Connect your DeepSeek API key. + + + Compare every language model provider Vapi supports. diff --git a/fern/providers/model/groq.mdx b/fern/providers/model/groq.mdx index a86a5ddc7..a30207117 100644 --- a/fern/providers/model/groq.mdx +++ b/fern/providers/model/groq.mdx @@ -5,140 +5,6 @@ description: Connect Groq to Vapi, choose a supported model, and configure it as slug: providers/model/groq --- -{/* Legacy marketing copy retained temporarily during provider-page standardization. - -**What is Groq?** - -Groq is a pioneering technology company specializing in high-performance AI inference solutions. Known for its innovative GroqChip, Groq delivers unparalleled speed and efficiency in AI processing. Their platform is designed to handle complex AI workloads with low latency, making it ideal for a variety of applications, including autonomous systems, data centers, and real-time AI inference. - - -**The Evolution of AI Inference:** - -AI inference has evolved significantly, from simple rule-based systems to advanced neural networks that require substantial computational power. Groq has harnessed cutting-edge advancements in hardware and software to create solutions that meet the growing demands for speed and accuracy in AI processing. - - -**Overview of Groq’s Offerings:** - -Groq offers a suite of high-performance AI tools and solutions designed to support various industries: - -**GroqChip:** - -The GroqChip is the cornerstone of Groq’s offerings, providing unmatched performance for AI inference tasks. Its architecture is optimized for low latency and high throughput, making it ideal for demanding AI applications. - -**GroqWare:** - -GroqWare is a suite of software tools that support the deployment and management of AI models on Groq hardware. It includes drivers, compilers, and libraries designed to optimize performance and simplify integration. - -**GroqCloud:** - -GroqCloud offers cloud-based access to Groq’s high-performance computing resources. This service allows businesses to leverage Groq’s powerful AI infrastructure without the need for significant capital investment in hardware. - -**High-Performance AI Inference:** - -Groq’s AI inference technology offers several key features and benefits: - -**Features:** - -- Low Latency: Ensures rapid processing of AI workloads. -- High Throughput: Capable of handling large volumes of data efficiently. -- Scalability: Easily scales to meet the demands of growing applications. - -**Benefits:** - -- Efficiency: Reduces the time required to process AI tasks. -- Reliability: Delivers consistent performance even under heavy loads. -- Cost-Effectiveness: Offers a competitive advantage with efficient resource utilization. - -**GroqChip Technology:** - -The GroqChip stands out for its advanced architecture and performance capabilities: - -**Architecture:** - -- Optimized Design: Tailored for AI inference with specialized processing units. -- High Efficiency: Maximizes performance per watt, reducing energy consumption. - -**Performance:** - -- Unmatched Speed: Delivers top-tier performance for real-time AI applications. -- Low Latency: Ensures minimal delay in processing, critical for time-sensitive tasks. - -**Applications:** - -- Autonomous Systems: Enhances the performance of self-driving cars and drones. -- Data Centers: Boosts the efficiency and capacity of AI data centers. - - -**Low Latency AI:** - -Groq’s low-latency AI solutions provide real-time processing capabilities essential for various applications: - -**Real-time Processing:** - -- Immediate Response: Critical for applications requiring instant decision-making. -- High Reliability: Ensures consistent performance with minimal delays. - -**Use Cases:** - -- AI Research: Accelerates experimentation and model testing. -- Autonomous Systems: Improves the safety and efficiency of autonomous vehicles. - -**Developer API and Tools:** - -Groq offers a comprehensive API and a range of development tools to facilitate integration and optimization: - -**Integration:** - -- SDKs: Available for multiple programming languages. -- Comprehensive Documentation: Guides and support for seamless implementation. - -**Use Cases:** - -Application Development: Streamline the integration of AI capabilities into applications. - -- Application Development: Streamline the integration of AI capabilities into applications. -- Research and Experimentation: Provides tools for efficient AI model deployment and testing. - - -**Use Cases for Groq:** - -Groq’s platform supports a wide range of applications across various industries: - -**AI Research:** - -Facilitates cutting-edge research with high-performance AI infrastructure. - - -**Autonomous Systems:** - -Enhances the capabilities of autonomous vehicles and robotics with low-latency processing. - - -**Data Centers:** - -Improves the efficiency and capacity of data centers handling AI workloads. - - -**Impact on AI Development:** - -Groq is transforming AI development by providing tools that enhance productivity and efficiency. By automating and optimizing AI inference, developers can focus on innovation and application rather than infrastructure management. - - -**Innovation and Research:** - -Groq is committed to continuous innovation and research in AI inference technology. Their team of experts focuses on advancing the capabilities of AI hardware and software, exploring new applications, and refining existing technologies to stay at the forefront of the industry. - - -**AI Safety and Ethics:** - -Ensuring the ethical use of AI is a core principle at Groq. They implement robust safeguards to prevent misuse of their technology and are actively involved in promoting responsible AI development. Protecting user data and maintaining transparency in AI operations are central to their mission. - -**Integrations and Compatibility:** - -Groq’s API allows seamless integration with various platforms and applications. This ensures that users can incorporate Groq’s AI capabilities into their existing systems effortlessly, enhancing functionality and improving user experience. - -*/} - Groq provides low-latency inference for supported open and partner models. In Vapi, Groq acts as the language model that generates your assistant's responses. You can use Groq through Vapi's default integration, or use your own Groq account by connecting it in [Integrations](/providers/integrations). @@ -152,7 +18,7 @@ curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \ -H "Authorization: Bearer $VAPI_API_KEY" \ -H "Content-Type: application/json" \ -d '{ - "model": { "provider": "groq", "model": "llama-3.3-70b-versatile" } + "model": { "provider": "groq", "model": "openai/gpt-oss-120b" } }' ``` @@ -164,6 +30,8 @@ These are the Groq models currently selectable in Vapi. | --- | --- | | GPT-OSS 20B | `openai/gpt-oss-20b` | | GPT-OSS 120B | `openai/gpt-oss-120b` | +| Kimi K2 Instruct 0905 | `moonshotai/kimi-k2-instruct-0905` | +| Llama 4 Scout 17B 16e Instruct | `meta-llama/llama-4-scout-17b-16e-instruct` | | Compound Beta | `compound-beta` | | Compound Beta Mini | `compound-beta-mini` | diff --git a/fern/providers/model/inflection-ai.mdx b/fern/providers/model/inflection-ai.mdx index 02a987c19..c65ce082f 100644 --- a/fern/providers/model/inflection-ai.mdx +++ b/fern/providers/model/inflection-ai.mdx @@ -1,22 +1,46 @@ --- title: Inflection AI -subtitle: Connect your Inflection AI account to Vapi. -description: Connect Inflection AI credentials to Vapi for use with supported integrations. +subtitle: Connect your Inflection AI account to use Inflection models in Vapi. +description: Connect an Inflection AI API key to Vapi and configure an assistant with a supported Inflection AI model. slug: providers/model/inflection-ai --- -Inflection AI is a large language model provider focused on conversational interactions. +Inflection AI is a large language model provider focused on conversational interactions. Connect your own Inflection AI account to use its models on a Vapi assistant. ## What is Inflection AI Inflection AI builds the Pi family of large language models, designed for conversational interactions. -Connect your Inflection AI account in [Integrations](/providers/integrations). Vapi does not currently list an Inflection AI model for new assistant configurations. +## Connect Inflection AI + +Inflection AI requires your own account. Connect your Inflection AI API key on the [Integrations](/providers/integrations) page before configuring an assistant. Without a connected Inflection AI key, the model below will not work. + +## Language model + +Set `model.provider` to `inflection-ai` and `model.model` to a supported model. + +```bash +curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \ + -H "Authorization: Bearer $VAPI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "model": { "provider": "inflection-ai", "model": "inflection_3_pi" } + }' +``` + +For additional API configuration options, review the [`InflectionAIModel` fields](/api-reference/assistants/create#request.body.model.InflectionAIModel) in the Create Assistant API reference. + +| Model | Model ID | +| --- | --- | +| Inflection 3 Pi | `inflection_3_pi` | ## Related - + - Connect and manage provider credentials. + Connect your Inflection AI API key. + + + Compare every language model provider Vapi supports. diff --git a/fern/providers/model/overview.mdx b/fern/providers/model/overview.mdx index 09c18bad4..c738f3c72 100644 --- a/fern/providers/model/overview.mdx +++ b/fern/providers/model/overview.mdx @@ -1,35 +1,38 @@ --- title: Model providers -subtitle: Look up the LLM providers Vapi supports, their IDs, and their compliance coverage. -description: Reference of every large language model provider Vapi supports, including provider IDs, HIPAA, GDPR, and PCI coverage, and where to configure each one. +subtitle: Look up the LLM providers Vapi supports and their IDs. +description: Reference of every large language model provider Vapi supports, including provider IDs and where to configure each one. slug: providers/model/overview --- -This page lists the large language model (LLM) providers Vapi supports, with each provider's ID, compliance coverage, and dedicated documentation. +This page lists the large language model (LLM) providers Vapi supports, with each provider's ID and dedicated documentation. The model is the LLM that generates your voice agent's responses. You select one by setting `model.provider` and `model.model` on an assistant. See [Create Assistant](/api-reference/assistants/create) in the API reference. ## Quick reference -Every column below reflects Vapi's coverage for that provider. The provider string is the exact value you pass in `model.provider`. Custom LLM is **N/A** because it runs on your own server, so whether it meets HIPAA, GDPR, or PCI is up to you to verify. - -| Provider | Provider string | HIPAA | GDPR (EU region) | PCI | -| -- | -- | -- | -- | -- | -| [Anthropic](/providers/model/anthropic#language-model) | `anthropic` | Yes | No {/* verify: model.options.ts says isEuropeSupported:false, MODEL_PROVIDER_METADATA says true */} | No | -| [Anthropic (Bedrock)](/providers/model/anthropic-bedrock#language-model) | `anthropic-bedrock` | Yes | Yes | Yes | -| [Anyscale](/providers/model/anyscale#language-model) | `anyscale` | No | No | No | -| [Azure OpenAI](/providers/model/azure-openai#language-model) | `azure-openai` | Yes | Yes | Yes | -| [Custom LLM](/customization/custom-llm/using-your-server) | `custom-llm` | N/A | N/A | N/A | -| [DeepInfra](/providers/model/deepinfra#language-model) | `deepinfra` | No | No | No | -| [Google](/providers/model/gemini#language-model) | `google` | Yes | Yes | Yes | -| [Groq](/providers/model/groq#language-model) | `groq` | No | No | No | -| [MiniMax](/providers/model/minimax#language-model) | `minimax` | No | No | No | -| [Mistral](/providers/model/mistral#language-model) | `mistral` | No | No | No | -| [OpenAI](/providers/model/openai#language-model) | `openai` | Yes | Yes | Yes | -| [OpenRouter](/providers/model/openrouter#language-model) | `openrouter` | No | No | No | -| [Perplexity](/providers/model/perplexity#language-model) | `perplexity-ai` | No | No | No | -| [Together AI](/providers/model/togetherai#language-model) | `together-ai` | Yes | No | No | -| [xAI](/providers/model/xai#language-model) | `xai` | Yes | Yes | No | +The provider string is the exact value you pass in `model.provider`. + +| Provider | Provider string | +| -- | -- | +| [Anthropic](/providers/model/anthropic#language-model) | `anthropic` | +| [Anthropic (Bedrock)](/providers/model/anthropic-bedrock#language-model) | `anthropic-bedrock` | +| [Anyscale](/providers/model/anyscale#language-model) | `anyscale` | +| [Azure OpenAI](/providers/model/azure-openai#language-model) | `azure-openai` | +| [Cerebras](/providers/model/cerebras#language-model) | `cerebras` | +| [Custom LLM](/customization/custom-llm/using-your-server) | `custom-llm` | +| [DeepInfra](/providers/model/deepinfra#language-model) | `deepinfra` | +| [DeepSeek](/providers/model/deepseek#language-model) | `deep-seek` | +| [Google](/providers/model/gemini#language-model) | `google` | +| [Groq](/providers/model/groq#language-model) | `groq` | +| [Inflection AI](/providers/model/inflection-ai#language-model) | `inflection-ai` | +| [MiniMax](/providers/model/minimax#language-model) | `minimax` | +| [Mistral](/providers/model/mistral#language-model) | `mistral` | +| [OpenAI](/providers/model/openai#language-model) | `openai` | +| [OpenRouter](/providers/model/openrouter#language-model) | `openrouter` | +| [Perplexity](/providers/model/perplexity#language-model) | `perplexity-ai` | +| [Together AI](/providers/model/togetherai#language-model) | `together-ai` | +| [xAI](/providers/model/xai#language-model) | `xai` | The **Assistant → Model** dropdown in the [Vapi Dashboard](https://dashboard.vapi.ai) is the most current list of selectable models. diff --git a/fern/providers/transcriber/azure.mdx b/fern/providers/transcriber/azure.mdx index 8ffae80f8..77e59a4a3 100644 --- a/fern/providers/transcriber/azure.mdx +++ b/fern/providers/transcriber/azure.mdx @@ -37,13 +37,13 @@ The following language codes are currently accepted by Vapi for this capability. | Language | Language code | | --- | --- | | Afrikaans (South Africa) | `af-ZA` | +| Albanian (Albania) | `sq-AL` | | Amharic (Ethiopia) | `am-ET` | -| Arabic (United Arab Emirates) | `ar-AE` | -| Arabic (Bahrain) | `ar-BH` | | Arabic (Algeria) | `ar-DZ` | +| Arabic (Bahrain) | `ar-BH` | | Arabic (Egypt) | `ar-EG` | -| Arabic (Israel) | `ar-IL` | | Arabic (Iraq) | `ar-IQ` | +| Arabic (Israel) | `ar-IL` | | Arabic (Jordan) | `ar-JO` | | Arabic (Kuwait) | `ar-KW` | | Arabic (Lebanon) | `ar-LB` | @@ -55,114 +55,119 @@ The following language codes are currently accepted by Vapi for this capability. | Arabic (Saudi Arabia) | `ar-SA` | | Arabic (Syria) | `ar-SY` | | Arabic (Tunisia) | `ar-TN` | +| Arabic (United Arab Emirates) | `ar-AE` | | Arabic (Yemen) | `ar-YE` | +| Armenian (Armenia) | `hy-AM` | | Azerbaijani (Azerbaijan) | `az-AZ` | -| Bulgarian (Bulgaria) | `bg-BG` | | Bangla (India) | `bn-IN` | +| Basque (Spain) | `eu-ES` | | Bosnian (Bosnia & Herzegovina) | `bs-BA` | +| Bulgarian (Bulgaria) | `bg-BG` | +| Burmese (Myanmar (Burma)) | `my-MM` | +| Cantonese (China) | `yue-CN` | | Catalan (Spain) | `ca-ES` | +| Chinese (China) | `zh-CN` | +| Chinese (China) | `zh-CN-shandong` | +| Chinese (China) | `zh-CN-sichuan` | +| Chinese (Hong Kong) | `zh-HK` | +| Chinese (Taiwan) | `zh-TW` | +| Croatian (Croatia) | `hr-HR` | | Czech (Czechia) | `cs-CZ` | -| Welsh (United Kingdom) | `cy-GB` | | Danish (Denmark) | `da-DK` | -| German (Austria) | `de-AT` | -| German (Switzerland) | `de-CH` | -| German (Germany) | `de-DE` | -| Greek (Greece) | `el-GR` | +| Dutch (Belgium) | `nl-BE` | +| Dutch (Netherlands) | `nl-NL` | | English (Australia) | `en-AU` | | English (Canada) | `en-CA` | -| English (United Kingdom) | `en-GB` | | English (Ghana) | `en-GH` | | English (Hong Kong) | `en-HK` | -| English (Ireland) | `en-IE` | | English (India) | `en-IN` | +| English (Ireland) | `en-IE` | | English (Kenya) | `en-KE` | -| English (Nigeria) | `en-NG` | | English (New Zealand) | `en-NZ` | +| English (Nigeria) | `en-NG` | | English (Philippines) | `en-PH` | | English (Singapore) | `en-SG` | +| English (South Africa) | `en-ZA` | | English (Tanzania) | `en-TZ` | +| English (United Kingdom) | `en-GB` | | English (United States) | `en-US` | -| English (South Africa) | `en-ZA` | -| Spanish (Argentina) | `es-AR` | -| Spanish (Bolivia) | `es-BO` | -| Spanish (Chile) | `es-CL` | -| Spanish (Colombia) | `es-CO` | -| Spanish (Costa Rica) | `es-CR` | -| Spanish (Cuba) | `es-CU` | -| Spanish (Dominican Republic) | `es-DO` | -| Spanish (Ecuador) | `es-EC` | -| Spanish (Spain) | `es-ES` | -| Spanish (Equatorial Guinea) | `es-GQ` | -| Spanish (Guatemala) | `es-GT` | -| Spanish (Honduras) | `es-HN` | -| Spanish (Mexico) | `es-MX` | -| Spanish (Nicaragua) | `es-NI` | -| Spanish (Panama) | `es-PA` | -| Spanish (Peru) | `es-PE` | -| Spanish (Puerto Rico) | `es-PR` | -| Spanish (Paraguay) | `es-PY` | -| Spanish (El Salvador) | `es-SV` | -| Spanish (United States) | `es-US` | -| Spanish (Uruguay) | `es-UY` | -| Spanish (Venezuela) | `es-VE` | | Estonian (Estonia) | `et-EE` | -| Basque (Spain) | `eu-ES` | -| Persian (Iran) | `fa-IR` | -| Finnish (Finland) | `fi-FI` | | Filipino (Philippines) | `fil-PH` | +| Finnish (Finland) | `fi-FI` | | French (Belgium) | `fr-BE` | | French (Canada) | `fr-CA` | -| French (Switzerland) | `fr-CH` | | French (France) | `fr-FR` | -| Irish (Ireland) | `ga-IE` | +| French (Switzerland) | `fr-CH` | | Galician (Spain) | `gl-ES` | +| Georgian (Georgia) | `ka-GE` | +| German (Austria) | `de-AT` | +| German (Germany) | `de-DE` | +| German (Switzerland) | `de-CH` | +| Greek (Greece) | `el-GR` | | Gujarati (India) | `gu-IN` | | Hebrew (Israel) | `he-IL` | | Hindi (India) | `hi-IN` | -| Croatian (Croatia) | `hr-HR` | | Hungarian (Hungary) | `hu-HU` | -| Armenian (Armenia) | `hy-AM` | -| Indonesian (Indonesia) | `id-ID` | | Icelandic (Iceland) | `is-IS` | -| Italian (Switzerland) | `it-CH` | +| Indonesian (Indonesia) | `id-ID` | +| Irish (Ireland) | `ga-IE` | | Italian (Italy) | `it-IT` | +| Italian (Switzerland) | `it-CH` | | Japanese (Japan) | `ja-JP` | | Javanese (Indonesia) | `jv-ID` | -| Georgian (Georgia) | `ka-GE` | +| Kannada (India) | `kn-IN` | | Kazakh (Kazakhstan) | `kk-KZ` | | Khmer (Cambodia) | `km-KH` | -| Kannada (India) | `kn-IN` | | Korean (South Korea) | `ko-KR` | | Lao (Laos) | `lo-LA` | -| Lithuanian (Lithuania) | `lt-LT` | | Latvian (Latvia) | `lv-LV` | +| Lithuanian (Lithuania) | `lt-LT` | | Macedonian (North Macedonia) | `mk-MK` | -| Malayalam (India) | `ml-IN` | -| Mongolian (Mongolia) | `mn-MN` | -| Marathi (India) | `mr-IN` | | Malay (Malaysia) | `ms-MY` | +| Malayalam (India) | `ml-IN` | | Maltese (Malta) | `mt-MT` | -| Burmese (Myanmar (Burma)) | `my-MM` | -| Norwegian Bokmål (Norway) | `nb-NO` | +| Marathi (India) | `mr-IN` | +| Mongolian (Mongolia) | `mn-MN` | | Nepali (Nepal) | `ne-NP` | -| Dutch (Belgium) | `nl-BE` | -| Dutch (Netherlands) | `nl-NL` | -| Punjabi (India) | `pa-IN` | -| Polish (Poland) | `pl-PL` | +| Norwegian Bokmål (Norway) | `nb-NO` | | Pashto (Afghanistan) | `ps-AF` | +| Persian (Iran) | `fa-IR` | +| Polish (Poland) | `pl-PL` | | Portuguese (Brazil) | `pt-BR` | | Portuguese (Portugal) | `pt-PT` | +| Punjabi (India) | `pa-IN` | | Romanian (Romania) | `ro-RO` | | Russian (Russia) | `ru-RU` | +| Serbian (Serbia) | `sr-RS` | | Sinhala (Sri Lanka) | `si-LK` | | Slovak (Slovakia) | `sk-SK` | | Slovenian (Slovenia) | `sl-SI` | | Somali (Somalia) | `so-SO` | -| Albanian (Albania) | `sq-AL` | -| Serbian (Serbia) | `sr-RS` | -| Swedish (Sweden) | `sv-SE` | +| Spanish (Argentina) | `es-AR` | +| Spanish (Bolivia) | `es-BO` | +| Spanish (Chile) | `es-CL` | +| Spanish (Colombia) | `es-CO` | +| Spanish (Costa Rica) | `es-CR` | +| Spanish (Cuba) | `es-CU` | +| Spanish (Dominican Republic) | `es-DO` | +| Spanish (Ecuador) | `es-EC` | +| Spanish (El Salvador) | `es-SV` | +| Spanish (Equatorial Guinea) | `es-GQ` | +| Spanish (Guatemala) | `es-GT` | +| Spanish (Honduras) | `es-HN` | +| Spanish (Mexico) | `es-MX` | +| Spanish (Nicaragua) | `es-NI` | +| Spanish (Panama) | `es-PA` | +| Spanish (Paraguay) | `es-PY` | +| Spanish (Peru) | `es-PE` | +| Spanish (Puerto Rico) | `es-PR` | +| Spanish (Spain) | `es-ES` | +| Spanish (United States) | `es-US` | +| Spanish (Uruguay) | `es-UY` | +| Spanish (Venezuela) | `es-VE` | | Swahili (Kenya) | `sw-KE` | | Swahili (Tanzania) | `sw-TZ` | +| Swedish (Sweden) | `sv-SE` | | Tamil (India) | `ta-IN` | | Telugu (India) | `te-IN` | | Thai (Thailand) | `th-TH` | @@ -171,13 +176,8 @@ The following language codes are currently accepted by Vapi for this capability. | Urdu (India) | `ur-IN` | | Uzbek (Uzbekistan) | `uz-UZ` | | Vietnamese (Vietnam) | `vi-VN` | +| Welsh (United Kingdom) | `cy-GB` | | wuu (China) | `wuu-CN` | -| Cantonese (China) | `yue-CN` | -| Chinese (China) | `zh-CN` | -| Chinese (China) | `zh-CN-shandong` | -| Chinese (China) | `zh-CN-sichuan` | -| Chinese (Hong Kong) | `zh-HK` | -| Chinese (Taiwan) | `zh-TW` | | Zulu (South Africa) | `zu-ZA` | ## Related diff --git a/fern/providers/transcriber/cartesia.mdx b/fern/providers/transcriber/cartesia.mdx index f96750eb6..12da11578 100644 --- a/fern/providers/transcriber/cartesia.mdx +++ b/fern/providers/transcriber/cartesia.mdx @@ -33,199 +33,113 @@ For additional API configuration options, review the [`CartesiaTranscriber` fiel | Model | Model ID | | --- | --- | | Ink Whisper | `ink-whisper` | -| Ink 2 | `ink-2` | ### Supported languages -The following language codes are currently accepted by Vapi for this capability. +The following language codes are currently accepted by Vapi for Cartesia. See Cartesia's [Ink Whisper API reference](https://docs.cartesia.ai/api-reference/stt/transcribe) for current provider details. | Language | Language code | | --- | --- | -| Afar | `aa` | -| Abkhazian | `ab` | -| Avestan | `ae` | | Afrikaans | `af` | -| Akan | `ak` | +| Albanian | `sq` | | Amharic | `am` | -| Aragonese | `an` | | Arabic | `ar` | +| Armenian | `hy` | | Assamese | `as` | -| Avaric | `av` | -| Aymara | `ay` | | Azerbaijani | `az` | | Bashkir | `ba` | +| Basque | `eu` | | Belarusian | `be` | -| Bulgarian | `bg` | -| Bhojpuri | `bh` | -| Bislama | `bi` | -| Bambara | `bm` | -| Bangla | `bn` | -| Tibetan | `bo` | -| Breton | `br` | +| Bengali | `bn` | | Bosnian | `bs` | +| Breton | `br` | +| Bulgarian | `bg` | +| Cantonese | `yue` | | Catalan | `ca` | -| Chechen | `ce` | -| Chamorro | `ch` | -| Corsican | `co` | -| Cree | `cr` | +| Chinese | `zh` | +| Croatian | `hr` | | Czech | `cs` | -| Church Slavic | `cu` | -| Chuvash | `cv` | -| Welsh | `cy` | | Danish | `da` | -| German | `de` | -| Divehi | `dv` | -| Dzongkha | `dz` | -| Ewe | `ee` | -| Greek | `el` | +| Dutch | `nl` | | English | `en` | -| Esperanto | `eo` | -| Spanish | `es` | | Estonian | `et` | -| Basque | `eu` | -| Persian | `fa` | -| Fula | `ff` | -| Finnish | `fi` | -| Fijian | `fj` | | Faroese | `fo` | +| Finnish | `fi` | | French | `fr` | -| Western Frisian | `fy` | -| Irish | `ga` | -| Scottish Gaelic | `gd` | | Galician | `gl` | -| Guarani | `gn` | +| Georgian | `ka` | +| German | `de` | +| Greek | `el` | | Gujarati | `gu` | -| Manx | `gv` | +| Haitian Creole | `ht` | | Hausa | `ha` | +| Hawaiian | `haw` | | Hebrew | `he` | | Hindi | `hi` | -| Hiri Motu | `ho` | -| Croatian | `hr` | -| Haitian Creole | `ht` | | Hungarian | `hu` | -| Armenian | `hy` | -| Herero | `hz` | -| Interlingua | `ia` | -| Indonesian | `id` | -| Interlingue | `ie` | -| Igbo | `ig` | -| Sichuan Yi | `ii` | -| Inupiaq | `ik` | -| Ido | `io` | | Icelandic | `is` | +| Indonesian | `id` | | Italian | `it` | -| Inuktitut | `iu` | | Japanese | `ja` | -| Javanese | `jv` | -| Georgian | `ka` | -| Kongo | `kg` | -| Kikuyu | `ki` | -| Kuanyama | `kj` | +| Javanese | `jw` | +| Kannada | `kn` | | Kazakh | `kk` | -| Kalaallisut | `kl` | | Khmer | `km` | -| Kannada | `kn` | | Korean | `ko` | -| Kanuri | `kr` | -| Kashmiri | `ks` | -| Kurdish | `ku` | -| Komi | `kv` | -| Cornish | `kw` | -| Kyrgyz | `ky` | +| Lao | `lo` | | Latin | `la` | -| Luxembourgish | `lb` | -| Ganda | `lg` | -| Limburgish | `li` | +| Latvian | `lv` | | Lingala | `ln` | -| Lao | `lo` | | Lithuanian | `lt` | -| Luba-Katanga | `lu` | -| Latvian | `lv` | -| Malagasy | `mg` | -| Marshallese | `mh` | -| Māori | `mi` | +| Luxembourgish | `lb` | | Macedonian | `mk` | -| Malayalam | `ml` | -| Mongolian | `mn` | -| Marathi | `mr` | +| Malagasy | `mg` | | Malay | `ms` | +| Malayalam | `ml` | | Maltese | `mt` | -| Burmese | `my` | -| Nauru | `na` | -| Norwegian Bokmål | `nb` | -| North Ndebele | `nd` | +| Maori | `mi` | +| Marathi | `mr` | +| Mongolian | `mn` | +| Myanmar (Burmese) | `my` | | Nepali | `ne` | -| Ndonga | `ng` | -| Dutch | `nl` | -| Norwegian Nynorsk | `nn` | | Norwegian | `no` | -| South Ndebele | `nr` | -| Navajo | `nv` | -| Nyanja | `ny` | +| Norwegian Nynorsk | `nn` | | Occitan | `oc` | -| Ojibwa | `oj` | -| Oromo | `om` | -| Odia | `or` | -| Ossetic | `os` | -| Punjabi | `pa` | -| Pali | `pi` | -| Polish | `pl` | | Pashto | `ps` | +| Persian | `fa` | +| Polish | `pl` | | Portuguese | `pt` | -| Quechua | `qu` | -| Romansh | `rm` | -| Rundi | `rn` | +| Punjabi | `pa` | | Romanian | `ro` | | Russian | `ru` | -| Kinyarwanda | `rw` | | Sanskrit | `sa` | -| Sardinian | `sc` | +| Serbian | `sr` | +| Shona | `sn` | | Sindhi | `sd` | -| Northern Sami | `se` | -| Sango | `sg` | | Sinhala | `si` | | Slovak | `sk` | | Slovenian | `sl` | -| Samoan | `sm` | -| Shona | `sn` | | Somali | `so` | -| Albanian | `sq` | -| Serbian | `sr` | -| Swati | `ss` | -| Southern Sotho | `st` | +| Spanish | `es` | | Sundanese | `su` | -| Swedish | `sv` | | Swahili | `sw` | +| Swedish | `sv` | +| Tagalog | `tl` | +| Tajik | `tg` | | Tamil | `ta` | +| Tatar | `tt` | | Telugu | `te` | -| Tajik | `tg` | | Thai | `th` | -| Tigrinya | `ti` | -| Turkmen | `tk` | -| Filipino | `tl` | -| Tswana | `tn` | -| Tongan | `to` | +| Tibetan | `bo` | | Turkish | `tr` | -| Tsonga | `ts` | -| Tatar | `tt` | -| Akan | `tw` | -| Tahitian | `ty` | -| Uyghur | `ug` | +| Turkmen | `tk` | | Ukrainian | `uk` | | Urdu | `ur` | | Uzbek | `uz` | -| Venda | `ve` | | Vietnamese | `vi` | -| Volapük | `vo` | -| Walloon | `wa` | -| Wolof | `wo` | -| Xhosa | `xh` | +| Welsh | `cy` | | Yiddish | `yi` | -| Cantonese | `yue` | | Yoruba | `yo` | -| Zhuang | `za` | -| Chinese | `zh` | -| Zulu | `zu` | ## Related diff --git a/fern/providers/transcriber/deepgram.mdx b/fern/providers/transcriber/deepgram.mdx index 06248818e..0ae856bf1 100644 --- a/fern/providers/transcriber/deepgram.mdx +++ b/fern/providers/transcriber/deepgram.mdx @@ -51,99 +51,90 @@ For additional API configuration options, review the [`DeepgramTranscriber` fiel ### Supported languages -The following language values are currently accepted by Vapi for this provider. +The matrix shows the language and model combinations currently supported by Vapi. -| Language | Language code | -| --- | --- | -| Arabic | `ar` | -| Azerbaijani | `az` | -| Bashkir | `ba` | -| Belarusian | `be` | -| Bulgarian | `bg` | -| Bangla | `bn` | -| Breton | `br` | -| Bosnian | `bs` | -| Catalan | `ca` | -| Czech | `cs` | -| Danish | `da` | -| Danish (Denmark) | `da-DK` | -| German | `de` | -| German (Switzerland) | `de-CH` | -| Greek | `el` | -| English | `en` | -| English (Australia) | `en-AU` | -| English (Canada) | `en-CA` | -| English (United Kingdom) | `en-GB` | -| English (Ireland) | `en-IE` | -| English (India) | `en-IN` | -| English (New Zealand) | `en-NZ` | -| English (United States) | `en-US` | -| Spanish | `es` | -| Spanish | `es-419` | -| Spanish | `es-LATAM` | -| Estonian | `et` | -| Basque | `eu` | -| Persian | `fa` | -| Finnish | `fi` | -| French | `fr` | -| French (Canada) | `fr-CA` | -| Hausa | `ha` | -| Hawaiian | `haw` | -| Hebrew | `he` | -| Hindi | `hi` | -| Hindi | `hi-Latn` | -| Croatian | `hr` | -| Hungarian | `hu` | -| Indonesian | `id` | -| Icelandic | `is` | -| Italian | `it` | -| Japanese | `ja` | -| Javanese | `jw` | -| Kannada | `kn` | -| Korean | `ko` | -| Korean (South Korea) | `ko-KR` | -| Lingala | `ln` | -| Lithuanian | `lt` | -| Latvian | `lv` | -| Macedonian | `mk` | -| Marathi | `mr` | -| Malay | `ms` | -| Multilingual | `multi` | -| Dutch | `nl` | -| Dutch (Belgium) | `nl-BE` | -| Norwegian | `no` | -| Polish | `pl` | -| Portuguese | `pt` | -| Portuguese (Brazil) | `pt-BR` | -| Portuguese (Portugal) | `pt-PT` | -| Romanian | `ro` | -| Russian | `ru` | -| Slovak | `sk` | -| Slovenian | `sl` | -| Shona | `sn` | -| Somali | `so` | -| Serbian | `sr` | -| Sundanese | `su` | -| Swedish | `sv` | -| Swedish (Sweden) | `sv-SE` | -| Tamil | `ta` | -| Tamasheq | `taq` | -| Telugu | `te` | -| Thai | `th` | -| Thai (Thailand) | `th-TH` | -| Filipino | `tl` | -| Turkish | `tr` | -| Tatar | `tt` | -| Ukrainian | `uk` | -| Urdu | `ur` | -| Vietnamese | `vi` | -| Yoruba | `yo` | -| Chinese | `zh` | -| Chinese (China) | `zh-CN` | -| Chinese (Hong Kong) | `zh-HK` | -| Chinese | `zh-Hans` | -| Chinese | `zh-Hant` | -| Chinese (Taiwan) | `zh-TW` | + +The Nova 3 column applies to Nova 3 and Nova 3 General, and the Nova 2 column applies to Nova 2 and Nova 2 General. Specialized Nova 2 includes Meeting, Phone Call, Finance, Conversational AI, Voicemail, Video, Medical, Drive-Thru, and Automotive. + + +| Language | Language code | Nova 3 | Nova 3 Medical | Nova 2 | Specialized Nova 2 | Flux General English | Flux General Multilingual | +| --- | --- | --- | --- | --- | --- | --- | --- | +| Arabic | `ar` | X | | | | | | +| Bangla | `bn` | X | | | | | | +| Belarusian | `be` | X | | | | | | +| Bosnian | `bs` | X | | | | | | +| Bulgarian | `bg` | X | | X | | | | +| Catalan | `ca` | X | | X | | | | +| Chinese | `zh` | X | | X | | | | +| Chinese (China) | `zh-CN` | X | | X | | | | +| Chinese (Hong Kong) | `zh-HK` | X | | X | | | | +| Chinese (Simplified) | `zh-Hans` | X | | X | | | | +| Chinese (Taiwan) | `zh-TW` | X | | X | | | | +| Chinese (Traditional) | `zh-Hant` | X | | X | | | | +| Croatian | `hr` | X | | | | | | +| Czech | `cs` | X | | X | | | | +| Danish | `da` | X | | X | | | | +| Danish (Denmark) | `da-DK` | X | | X | | | | +| Dutch | `nl` | X | | X | | | X | +| Dutch (Belgium) | `nl-BE` | X | | X | | | | +| English | `en` | X | X | X | X | X | X | +| English (Australia) | `en-AU` | X | X | X | | | | +| English (Canada) | `en-CA` | | X | | | | | +| English (India) | `en-IN` | X | X | X | | | | +| English (Ireland) | `en-IE` | | X | | | | | +| English (New Zealand) | `en-NZ` | X | X | X | | | | +| English (United Kingdom) | `en-GB` | X | X | X | | | | +| English (United States) | `en-US` | X | X | X | X | | | +| Estonian | `et` | X | | X | | | | +| Filipino | `tl` | X | | | | | | +| Finnish | `fi` | X | | X | | | | +| French | `fr` | X | | X | | | X | +| French (Canada) | `fr-CA` | X | | X | | | | +| German | `de` | X | | X | | | X | +| German (Switzerland) | `de-CH` | X | | X | | | | +| Greek | `el` | X | | X | | | | +| Hebrew | `he` | X | | | | | | +| Hindi | `hi` | X | | X | | | X | +| Hungarian | `hu` | X | | X | | | | +| Indonesian | `id` | X | | X | | | | +| Italian | `it` | X | | X | | | X | +| Japanese | `ja` | X | | X | | | X | +| Kannada | `kn` | X | | | | | | +| Korean | `ko` | X | | X | | | | +| Korean (South Korea) | `ko-KR` | X | | X | | | | +| Latvian | `lv` | X | | X | | | | +| Lithuanian | `lt` | X | | X | | | | +| Macedonian | `mk` | X | | | | | | +| Malay | `ms` | X | | X | | | | +| Marathi | `mr` | X | | | | | | +| Multilingual | `multi` | X | | X | | | | +| Norwegian | `no` | X | | X | | | | +| Persian | `fa` | X | | | | | | +| Polish | `pl` | X | | X | | | | +| Portuguese | `pt` | X | | X | | | X | +| Portuguese (Brazil) | `pt-BR` | X | | X | | | | +| Portuguese (Portugal) | `pt-PT` | X | | X | | | | +| Romanian | `ro` | X | | X | | | | +| Russian | `ru` | X | | X | | | X | +| Serbian | `sr` | X | | | | | | +| Slovak | `sk` | X | | X | | | | +| Slovenian | `sl` | X | | | | | | +| Spanish | `es` | X | | X | | | X | +| Spanish (Latin America) | `es-419` | X | | X | | | | +| Swedish | `sv` | X | | X | | | | +| Swedish (Sweden) | `sv-SE` | X | | X | | | | +| Tamil | `ta` | X | | | | | | +| Telugu | `te` | X | | | | | | +| Thai | `th` | X | | X | | | | +| Thai (Thailand) | `th-TH` | X | | X | | | | +| Turkish | `tr` | X | | X | | | | +| Ukrainian | `uk` | X | | X | | | | +| Urdu | `ur` | X | | | | | | +| Vietnamese | `vi` | X | | X | | | | + +### Multilingual transcription + +For Nova 3 or Nova 2, set `transcriber.language` to `multi`. For Flux, select `flux-general-multi` and omit `transcriber.languages` to use automatic language detection. You can also provide a `languages` array to give Flux language hints for multilingual or code-switching conversations. See [Deepgram's Flux language prompting documentation](https://developers.deepgram.com/docs/flux/language-prompting). ## Related diff --git a/fern/providers/transcriber/elevenlabs.mdx b/fern/providers/transcriber/elevenlabs.mdx index 2b5c257cd..85b1e2ce9 100644 --- a/fern/providers/transcriber/elevenlabs.mdx +++ b/fern/providers/transcriber/elevenlabs.mdx @@ -24,7 +24,7 @@ curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \ -H "Authorization: Bearer $VAPI_API_KEY" \ -H "Content-Type: application/json" \ -d '{ - "transcriber": { "provider": "11labs", "model": "scribe_v1" } + "transcriber": { "provider": "11labs", "model": "scribe_v2_realtime" } }' ``` @@ -38,194 +38,103 @@ For additional API configuration options, review the [`ElevenLabsTranscriber` fi ### Supported languages -The following language codes are currently accepted by Vapi for this capability. +The following languages are supported by the current Scribe models and accepted by Vapi. See [ElevenLabs' speech-to-text documentation](https://elevenlabs.io/docs/overview/capabilities/speech-to-text/#supported-languages) for provider details. | Language | Language code | | --- | --- | -| Afar | `aa` | -| Abkhazian | `ab` | -| Avestan | `ae` | | Afrikaans | `af` | -| Akan | `ak` | | Amharic | `am` | -| Aragonese | `an` | | Arabic | `ar` | +| Armenian | `hy` | | Assamese | `as` | -| Avaric | `av` | -| Aymara | `ay` | | Azerbaijani | `az` | -| Bashkir | `ba` | | Belarusian | `be` | -| Bulgarian | `bg` | -| Bhojpuri | `bh` | -| Bislama | `bi` | -| Bambara | `bm` | -| Bangla | `bn` | -| Tibetan | `bo` | -| Breton | `br` | +| Bengali | `bn` | | Bosnian | `bs` | +| Bulgarian | `bg` | +| Burmese | `my` | +| Cantonese | `yue` | | Catalan | `ca` | -| Chechen | `ce` | -| Chamorro | `ch` | -| Corsican | `co` | -| Cree | `cr` | +| Chichewa | `ny` | +| Chinese | `zh` | +| Croatian | `hr` | | Czech | `cs` | -| Church Slavic | `cu` | -| Chuvash | `cv` | -| Welsh | `cy` | | Danish | `da` | -| German | `de` | -| Divehi | `dv` | -| Dzongkha | `dz` | -| Ewe | `ee` | -| Greek | `el` | +| Dutch | `nl` | | English | `en` | -| Esperanto | `eo` | -| Spanish | `es` | | Estonian | `et` | -| Basque | `eu` | -| Persian | `fa` | -| Fula | `ff` | +| Filipino | `tl` | | Finnish | `fi` | -| Fijian | `fj` | -| Faroese | `fo` | | French | `fr` | -| Western Frisian | `fy` | -| Irish | `ga` | -| Scottish Gaelic | `gd` | +| Fula | `ff` | | Galician | `gl` | -| Guarani | `gn` | +| Ganda | `lg` | +| Georgian | `ka` | +| German | `de` | +| Greek | `el` | | Gujarati | `gu` | -| Manx | `gv` | | Hausa | `ha` | | Hebrew | `he` | | Hindi | `hi` | -| Hiri Motu | `ho` | -| Croatian | `hr` | -| Haitian Creole | `ht` | | Hungarian | `hu` | -| Armenian | `hy` | -| Herero | `hz` | -| Interlingua | `ia` | -| Indonesian | `id` | -| Interlingue | `ie` | -| Igbo | `ig` | -| Sichuan Yi | `ii` | -| Inupiaq | `ik` | -| Ido | `io` | | Icelandic | `is` | +| Igbo | `ig` | +| Indonesian | `id` | +| Irish | `ga` | | Italian | `it` | -| Inuktitut | `iu` | | Japanese | `ja` | | Javanese | `jv` | -| Georgian | `ka` | -| Kongo | `kg` | -| Kikuyu | `ki` | -| Kuanyama | `kj` | +| Kannada | `kn` | | Kazakh | `kk` | -| Kalaallisut | `kl` | | Khmer | `km` | -| Kannada | `kn` | | Korean | `ko` | -| Kanuri | `kr` | -| Kashmiri | `ks` | | Kurdish | `ku` | -| Komi | `kv` | -| Cornish | `kw` | | Kyrgyz | `ky` | -| Latin | `la` | -| Luxembourgish | `lb` | -| Ganda | `lg` | -| Limburgish | `li` | -| Lingala | `ln` | | Lao | `lo` | -| Lithuanian | `lt` | -| Luba-Katanga | `lu` | | Latvian | `lv` | -| Malagasy | `mg` | -| Marshallese | `mh` | -| Māori | `mi` | +| Lingala | `ln` | +| Lithuanian | `lt` | +| Luxembourgish | `lb` | | Macedonian | `mk` | -| Malayalam | `ml` | -| Mongolian | `mn` | -| Marathi | `mr` | | Malay | `ms` | +| Malayalam | `ml` | | Maltese | `mt` | -| Burmese | `my` | -| Nauru | `na` | -| Norwegian Bokmål | `nb` | -| North Ndebele | `nd` | +| Marathi | `mr` | +| Mongolian | `mn` | +| Māori | `mi` | | Nepali | `ne` | -| Ndonga | `ng` | -| Dutch | `nl` | -| Norwegian Nynorsk | `nn` | | Norwegian | `no` | -| South Ndebele | `nr` | -| Navajo | `nv` | -| Nyanja | `ny` | | Occitan | `oc` | -| Ojibwa | `oj` | -| Oromo | `om` | | Odia | `or` | -| Ossetic | `os` | -| Punjabi | `pa` | -| Pali | `pi` | -| Polish | `pl` | | Pashto | `ps` | +| Persian | `fa` | +| Polish | `pl` | | Portuguese | `pt` | -| Quechua | `qu` | -| Romansh | `rm` | -| Rundi | `rn` | +| Punjabi | `pa` | | Romanian | `ro` | | Russian | `ru` | -| Kinyarwanda | `rw` | -| Sanskrit | `sa` | -| Sardinian | `sc` | +| Serbian | `sr` | +| Shona | `sn` | | Sindhi | `sd` | -| Northern Sami | `se` | -| Sango | `sg` | -| Sinhala | `si` | | Slovak | `sk` | | Slovenian | `sl` | -| Samoan | `sm` | -| Shona | `sn` | | Somali | `so` | -| Albanian | `sq` | -| Serbian | `sr` | -| Swati | `ss` | -| Southern Sotho | `st` | -| Sundanese | `su` | -| Swedish | `sv` | +| Spanish | `es` | | Swahili | `sw` | +| Swedish | `sv` | +| Tajik | `tg` | | Tamil | `ta` | | Telugu | `te` | -| Tajik | `tg` | | Thai | `th` | -| Tigrinya | `ti` | -| Turkmen | `tk` | -| Filipino | `tl` | -| Tswana | `tn` | -| Tongan | `to` | | Turkish | `tr` | -| Tsonga | `ts` | -| Tatar | `tt` | -| Akan | `tw` | -| Tahitian | `ty` | -| Uyghur | `ug` | | Ukrainian | `uk` | | Urdu | `ur` | | Uzbek | `uz` | -| Venda | `ve` | | Vietnamese | `vi` | -| Volapük | `vo` | -| Walloon | `wa` | +| Welsh | `cy` | | Wolof | `wo` | | Xhosa | `xh` | -| Yiddish | `yi` | -| Cantonese | `yue` | | Yoruba | `yo` | -| Zhuang | `za` | -| Chinese | `zh` | | Zulu | `zu` | ## Related diff --git a/fern/providers/transcriber/gladia.mdx b/fern/providers/transcriber/gladia.mdx index a4bdd1212..c51926436 100644 --- a/fern/providers/transcriber/gladia.mdx +++ b/fern/providers/transcriber/gladia.mdx @@ -5,61 +5,6 @@ description: Configure a Gladia transcription model, language, and provider sett slug: providers/transcriber/gladia --- -{/* Legacy marketing copy retained temporarily during provider-page standardization. - -## What is Gladia? -Gladia is a state-of-the-art audio transcription and intelligence platform. It provides **real-time** speech-to-text for audio and video and adds advanced audio-intelligence features so you can turn unstructured audio into actionable insights. It integrates easily and scales so you can focus on building features instead of transcription infrastructure. -Try Gladia on their [playground](https://app.gladia.io/?utm_source=vapi) to get a feel for the product! - -## Why choose Gladia on Vapi for speech-to-text? - -### Low latency transcription -Gladia delivers low-latency live transcription, often under ~600 ms, for calls and streaming audio, with super-fast partials around ~300 ms for immediate response processing. It provides word-level timestamps and detailed custom vocabulary to power downstream workflows. - -### Global language coverage -Gladia supports **110+ languages** and dialects and robustly handles multilingual and mixed-language audio. It also supports mixed-language and code-switch scenarios for natural conversations and multilingual conversations. - -### Audio intelligence add-ons -Translation is available in one API call to one or more target languages. Gladia also offers summarization post-call, sentiment analysis, and named-entity recognition in real-time, enabling meeting notes, customer-call insights, and content production workflows on top of transcripts. - -### API and integrations -Gladia offers telephony compatibility (SIP/VoIP) and noise resistance for live use cases, and supports real-time streaming with low-latency interfaces for platforms and contact centers. It also provides a developer-friendly playground to test and monitor your transcription workflows. - -## Getting started - -1. Go to the **Assistants** tab in the left-hand navigation. -2. Create a new assistant, or select the voice assistant you want to configure. -3. Open the **Transcriber** tab in the top navigation (or scroll to the Transcriber module). -4. In the **Provider** dropdown, select **Gladia**. - -Watch the [Vapi x Gladia demo video](https://youtu.be/7EoYnMOHR5A?si=dIDTTXw2L--DY-QY) to see real-time features in action! - -## Best practices - -- **Region selection**: Use the region closest to your users; EU and US options are available for data residency and latency. -- **Custom vocabulary**: Add domain-specific terms (product names, acronyms) to improve accuracy. -- **Timestamps**: Use word-level timestamps when you need precise analytics or subtitles. -- **Translation**: Use built-in translation when you need multilingual outputs from a single stream. - -## Use cases - -- **Voice agents**: Real-time transcription, speaker attribution, translation, and post-call summaries. -- **Virtual meetings**: Live transcription, speaker attribution, translation, and meeting notes. -- **Customer service / contact centers**: Live call transcription, sentiment/keyword extraction, multilingual agent assistance. -- **Sales enablement**: Capture names, emails, and details across languages and accents; feed CRMs. -- **Media & content creation**: Transcribe/edit audio/video, generate subtitles (SRT/VTT), and translate for global distribution. - -## Data protection and compliance - -Gladia offers enterprise-grade data governance, secure hosting options, and alignment with privacy and compliance frameworks such as GDPR. EU and US regions are available for data residency. - -## Useful links -- **Playground**: [app.gladia.io](https://app.gladia.io/?utm_source=vapi) -- **Website**: [gladia.io](https://gladia.io/?utm_source=vapi) -- **Documentation**: [docs.gladia.io](https://docs.gladia.io/?utm_source=vapi) - -*/} - ## Speech-to-text Set `transcriber.provider` to `gladia`. Vapi supports Gladia's real-time transcription models, automatic or manual language selection, partial transcripts, audio enhancement, and custom vocabulary controls. @@ -87,7 +32,7 @@ For additional API configuration options, review the [`GladiaTranscriber` fields | Field | Required | Description | | --- | --- | --- | | `provider` | Yes | Set to `gladia`. | -| `model` | No | Gladia model to use. Defaults to `fast`. | +| `model` | No | Gladia model to use. Vapi defaults to `fast`. | | `languageBehaviour` | No | How Gladia selects languages. Defaults to `automatic single language`. | | `language` | For manual single-language transcription | One supported language code. | | `languages` | For manual multilingual transcription | An array of supported language codes. | diff --git a/fern/providers/transcriber/google.mdx b/fern/providers/transcriber/google.mdx index 2a00d0283..997ccc744 100644 --- a/fern/providers/transcriber/google.mdx +++ b/fern/providers/transcriber/google.mdx @@ -36,7 +36,7 @@ For additional API configuration options, review the [`GoogleTranscriber` fields | Gemini 2.0 Flash Lite | `gemini-2.0-flash-lite` | | Gemini 1.5 Pro | `gemini-1.5-pro` | -Google transcription is multilingual by default and supports a [wide range of languages](https://ai.google.dev/gemini-api/docs/models/gemini#available-languages). +Vapi defaults Google transcription to English. Set `transcriber.language` to `Multilingual` to use multilingual transcription; the value is case-sensitive. Google's [available languages](https://ai.google.dev/gemini-api/docs/models/gemini#available-languages) describe provider-level coverage, while the table below contains the language values accepted by Vapi. ### Supported languages @@ -44,7 +44,6 @@ The following language values are currently accepted by Vapi for this provider. | Language | Language value | | --- | --- | -| Multilingual | `Multilingual` | | Arabic | `Arabic` | | Bengali | `Bengali` | | Bulgarian | `Bulgarian` | @@ -68,6 +67,7 @@ The following language values are currently accepted by Vapi for this provider. | Korean | `Korean` | | Latvian | `Latvian` | | Lithuanian | `Lithuanian` | +| Multilingual | `Multilingual` | | Norwegian | `Norwegian` | | Polish | `Polish` | | Portuguese | `Portuguese` | diff --git a/fern/providers/transcriber/openai.mdx b/fern/providers/transcriber/openai.mdx index e010c97c0..dbce67e5f 100644 --- a/fern/providers/transcriber/openai.mdx +++ b/fern/providers/transcriber/openai.mdx @@ -56,6 +56,7 @@ The following language values are currently accepted by Vapi for this provider. | Dutch | `nl` | | English | `en` | | Estonian | `et` | +| Filipino | `tl` | | Finnish | `fi` | | French | `fr` | | Galician | `gl` | @@ -90,7 +91,6 @@ The following language values are currently accepted by Vapi for this provider. | Spanish | `es` | | Swahili | `sw` | | Swedish | `sv` | -| Filipino | `tl` | | Tamil | `ta` | | Thai | `th` | | Turkish | `tr` | diff --git a/fern/providers/transcriber/overview.mdx b/fern/providers/transcriber/overview.mdx index 5515886b1..e909d3480 100644 --- a/fern/providers/transcriber/overview.mdx +++ b/fern/providers/transcriber/overview.mdx @@ -1,38 +1,34 @@ --- title: Transcribers (Speech-to-text) -subtitle: Look up the speech-to-text providers Vapi supports and their compliance coverage. -description: Reference of every speech-to-text provider Vapi supports, including provider IDs, HIPAA and GDPR (EU) coverage, and where to configure each one. +subtitle: Look up the speech-to-text providers Vapi supports and their IDs. +description: Reference of every speech-to-text provider Vapi supports, including provider IDs and where to configure each one. slug: providers/transcriber/overview --- -This page lists the speech-to-text (STT) providers Vapi supports, with each provider's ID and compliance coverage. +This page lists the speech-to-text (STT) providers Vapi supports, with each provider's ID. The transcriber converts the caller's speech to text for your voice agent. You select one by setting `transcriber.provider` and `transcriber.model` on an assistant. See [Create Assistant](/api-reference/assistants/create) in the API reference. +Language coverage and automatic detection behavior can vary by model within the same provider. Review the provider page before choosing a model and language combination. + ## Quick reference -Every column reflects Vapi's coverage for that provider. The provider string is the exact value you pass in `transcriber.provider`. - -| Provider | Provider string | HIPAA | GDPR (EU region) | PCI | -| -- | -- | -- | -- | -- | -| [AssemblyAI](/providers/transcriber/assembly-ai#speech-to-text) | `assembly-ai` | No | No | No | -| [Azure](/providers/transcriber/azure#speech-to-text) | `azure` | Yes | No | Yes | -| [Cartesia](/providers/transcriber/cartesia#speech-to-text) | `cartesia` | Yes | Yes | No | -| [Deepgram](/providers/transcriber/deepgram#speech-to-text) | `deepgram` | Yes | Yes | Yes | -| [ElevenLabs](/providers/transcriber/elevenlabs#speech-to-text) | `11labs` | No | No | No | -| [Gladia](/providers/transcriber/gladia#speech-to-text) | `gladia` | No | No | No | -| [Google](/providers/transcriber/google#speech-to-text) | `google` | No | No | No | -| [OpenAI](/providers/transcriber/openai#speech-to-text) | `openai` | No | Yes | No | -| [Soniox](/providers/transcriber/soniox#speech-to-text) | `soniox` | Yes | Yes | No | -| [Speechmatics](/providers/transcriber/speechmatics#speech-to-text) | `speechmatics` | No | No | No | -| [Talkscriber](/providers/transcriber/talkscriber#speech-to-text) | `talkscriber` | No | No | No | -| [xAI](/providers/transcriber/xai#speech-to-text) | `xai` | Yes | Yes | No | - -{/* verify: transcribers have no per-provider PCI flag; PCI here is from the fallback-compliance rule -(only Deepgram + Azure are PCI-compliant transcribers, per issueActionMap); confirm. HIPAA from -HIPAA_COMPLIANT_TRANSCRIBER_PROVIDERS; EU from transcriberConstants. Vapi (white-label transcriber) -omitted because it is gated by enable-vapi-transcriber. Azure/Cartesia/ElevenLabs link to their voice pages -(same provider string spans voice+STT); Google→gemini and OpenAI→model/openai (merged). */} +The provider string is the exact value you pass in `transcriber.provider`. + +| Provider | Provider string | +| -- | -- | +| [AssemblyAI](/providers/transcriber/assembly-ai#speech-to-text) | `assembly-ai` | +| [Azure](/providers/transcriber/azure#speech-to-text) | `azure` | +| [Cartesia](/providers/transcriber/cartesia#speech-to-text) | `cartesia` | +| [Deepgram](/providers/transcriber/deepgram#speech-to-text) | `deepgram` | +| [ElevenLabs](/providers/transcriber/elevenlabs#speech-to-text) | `11labs` | +| [Gladia](/providers/transcriber/gladia#speech-to-text) | `gladia` | +| [Google](/providers/transcriber/google#speech-to-text) | `google` | +| [OpenAI](/providers/transcriber/openai#speech-to-text) | `openai` | +| [Soniox](/providers/transcriber/soniox#speech-to-text) | `soniox` | +| [Speechmatics](/providers/transcriber/speechmatics#speech-to-text) | `speechmatics` | +| [Talkscriber](/providers/transcriber/talkscriber#speech-to-text) | `talkscriber` | +| [xAI](/providers/transcriber/xai#speech-to-text) | `xai` | ## Related diff --git a/fern/providers/transcriber/soniox.mdx b/fern/providers/transcriber/soniox.mdx index bde1b6466..c4e795601 100644 --- a/fern/providers/transcriber/soniox.mdx +++ b/fern/providers/transcriber/soniox.mdx @@ -13,237 +13,100 @@ Soniox provides low-latency, multilingual transcription and semantic endpointing ## Speech-to-text -### Connect Soniox - -Configure Soniox in the Vapi Dashboard or update an assistant through the API. - - - - - - In the [Vapi Dashboard](https://dashboard.vapi.ai), open **Assistants**, then select the assistant you want to update. - - - Open the **Transcriber** settings. Set **Provider** to **Soniox** and **Model** to **stt-rt-v5**. - - - Click **Publish** to apply the new transcriber configuration. - - - - - Set `VAPI_API_KEY` in your environment with a [Vapi API key](/security-and-privacy/api-keys), then replace `YOUR_ASSISTANT_ID` with the assistant ID. - - Set `transcriber.provider` to `soniox` and `transcriber.model` to `stt-rt-v5`. - - ```bash - curl -X PATCH "https://api.vapi.ai/assistant/YOUR_ASSISTANT_ID" \ - -H "Authorization: Bearer $VAPI_API_KEY" \ - -H "Content-Type: application/json" \ - -d '{ - "transcriber": { - "provider": "soniox", - "model": "stt-rt-v5", - "language": "en" - } - }' - ``` - - For additional API configuration options, review the [`SonioxTranscriber` fields](/api-reference/assistants/create#request.body.transcriber.SonioxTranscriber) in the Create Assistant API reference. - - +Set `transcriber.provider` to `soniox` and `transcriber.model` to `stt-rt-v5`. Set `transcriber.languages` to an empty array for automatic language detection. + +```bash +curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \ + -H "Authorization: Bearer $VAPI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "transcriber": { + "provider": "soniox", + "model": "stt-rt-v5", + "languages": [] + } + }' +``` + +For additional API configuration options, review the [`SonioxTranscriber` fields](/api-reference/assistants/create#request.body.transcriber.SonioxTranscriber) in the Create Assistant API reference. + +### Supported models + +| Model | Model ID | +| --- | --- | +| Soniox STT Real-Time v4 | `stt-rt-v4` | +| Soniox STT Real-Time v5 | `stt-rt-v5` | + +### Automatic language detection + +Set `transcriber.languages` to an empty array to let Soniox automatically detect and transcribe any supported language, including code-switching within a conversation. You can provide expected language codes, such as `["en", "es"]`, instead. Vapi defaults `transcriber.languageHintsStrict` to `true`, which restricts transcription to the provided languages. Set it to `false` to use the values as hints while allowing other supported languages. See [Soniox language hints](https://soniox.com/docs/stt/concepts/language-hints) for provider details. ### Supported languages -The following language codes are currently accepted by Vapi for this capability. +The following languages are currently accepted by Vapi for Soniox. See [Soniox supported languages](https://soniox.com/docs/stt/concepts/supported-languages) for provider details. | Language | Language code | | --- | --- | -| Afar | `aa` | -| Abkhazian | `ab` | -| Avestan | `ae` | | Afrikaans | `af` | -| Akan | `ak` | -| Amharic | `am` | -| Aragonese | `an` | +| Albanian | `sq` | | Arabic | `ar` | -| Assamese | `as` | -| Avaric | `av` | -| Aymara | `ay` | | Azerbaijani | `az` | -| Bashkir | `ba` | +| Basque | `eu` | | Belarusian | `be` | -| Bulgarian | `bg` | -| Bhojpuri | `bh` | -| Bislama | `bi` | -| Bambara | `bm` | -| Bangla | `bn` | -| Tibetan | `bo` | -| Breton | `br` | +| Bengali | `bn` | | Bosnian | `bs` | +| Bulgarian | `bg` | | Catalan | `ca` | -| Chechen | `ce` | -| Chamorro | `ch` | -| Corsican | `co` | -| Cree | `cr` | +| Chinese | `zh` | +| Croatian | `hr` | | Czech | `cs` | -| Church Slavic | `cu` | -| Chuvash | `cv` | -| Welsh | `cy` | | Danish | `da` | -| German | `de` | -| Divehi | `dv` | -| Dzongkha | `dz` | -| Ewe | `ee` | -| Greek | `el` | +| Dutch | `nl` | | English | `en` | -| Esperanto | `eo` | -| Spanish | `es` | | Estonian | `et` | -| Basque | `eu` | -| Persian | `fa` | -| Fula | `ff` | | Finnish | `fi` | -| Fijian | `fj` | -| Faroese | `fo` | | French | `fr` | -| Western Frisian | `fy` | -| Irish | `ga` | -| Scottish Gaelic | `gd` | | Galician | `gl` | -| Guarani | `gn` | +| German | `de` | +| Greek | `el` | | Gujarati | `gu` | -| Manx | `gv` | -| Hausa | `ha` | | Hebrew | `he` | | Hindi | `hi` | -| Hiri Motu | `ho` | -| Croatian | `hr` | -| Haitian Creole | `ht` | | Hungarian | `hu` | -| Armenian | `hy` | -| Herero | `hz` | -| Interlingua | `ia` | | Indonesian | `id` | -| Interlingue | `ie` | -| Igbo | `ig` | -| Sichuan Yi | `ii` | -| Inupiaq | `ik` | -| Ido | `io` | -| Icelandic | `is` | | Italian | `it` | -| Inuktitut | `iu` | | Japanese | `ja` | -| Javanese | `jv` | -| Georgian | `ka` | -| Kongo | `kg` | -| Kikuyu | `ki` | -| Kuanyama | `kj` | -| Kazakh | `kk` | -| Kalaallisut | `kl` | -| Khmer | `km` | | Kannada | `kn` | +| Kazakh | `kk` | | Korean | `ko` | -| Kanuri | `kr` | -| Kashmiri | `ks` | -| Kurdish | `ku` | -| Komi | `kv` | -| Cornish | `kw` | -| Kyrgyz | `ky` | -| Latin | `la` | -| Luxembourgish | `lb` | -| Ganda | `lg` | -| Limburgish | `li` | -| Lingala | `ln` | -| Lao | `lo` | -| Lithuanian | `lt` | -| Luba-Katanga | `lu` | | Latvian | `lv` | -| Malagasy | `mg` | -| Marshallese | `mh` | -| Māori | `mi` | +| Lithuanian | `lt` | | Macedonian | `mk` | +| Malay | `ms` | | Malayalam | `ml` | -| Mongolian | `mn` | | Marathi | `mr` | -| Malay | `ms` | -| Maltese | `mt` | -| Burmese | `my` | -| Nauru | `na` | -| Norwegian Bokmål | `nb` | -| North Ndebele | `nd` | -| Nepali | `ne` | -| Ndonga | `ng` | -| Dutch | `nl` | -| Norwegian Nynorsk | `nn` | | Norwegian | `no` | -| South Ndebele | `nr` | -| Navajo | `nv` | -| Nyanja | `ny` | -| Occitan | `oc` | -| Ojibwa | `oj` | -| Oromo | `om` | -| Odia | `or` | -| Ossetic | `os` | -| Punjabi | `pa` | -| Pali | `pi` | +| Persian | `fa` | | Polish | `pl` | -| Pashto | `ps` | | Portuguese | `pt` | -| Quechua | `qu` | -| Romansh | `rm` | -| Rundi | `rn` | +| Punjabi | `pa` | | Romanian | `ro` | | Russian | `ru` | -| Kinyarwanda | `rw` | -| Sanskrit | `sa` | -| Sardinian | `sc` | -| Sindhi | `sd` | -| Northern Sami | `se` | -| Sango | `sg` | -| Sinhala | `si` | +| Serbian | `sr` | | Slovak | `sk` | | Slovenian | `sl` | -| Samoan | `sm` | -| Shona | `sn` | -| Somali | `so` | -| Albanian | `sq` | -| Serbian | `sr` | -| Swati | `ss` | -| Southern Sotho | `st` | -| Sundanese | `su` | -| Swedish | `sv` | +| Spanish | `es` | | Swahili | `sw` | +| Swedish | `sv` | +| Tagalog | `tl` | | Tamil | `ta` | | Telugu | `te` | -| Tajik | `tg` | | Thai | `th` | -| Tigrinya | `ti` | -| Turkmen | `tk` | -| Filipino | `tl` | -| Tswana | `tn` | -| Tongan | `to` | | Turkish | `tr` | -| Tsonga | `ts` | -| Tatar | `tt` | -| Akan | `tw` | -| Tahitian | `ty` | -| Uyghur | `ug` | | Ukrainian | `uk` | | Urdu | `ur` | -| Uzbek | `uz` | -| Venda | `ve` | | Vietnamese | `vi` | -| Volapük | `vo` | -| Walloon | `wa` | -| Wolof | `wo` | -| Xhosa | `xh` | -| Yiddish | `yi` | -| Cantonese | `yue` | -| Yoruba | `yo` | -| Zhuang | `za` | -| Chinese | `zh` | -| Zulu | `zu` | +| Welsh | `cy` | ## Related diff --git a/fern/providers/transcriber/speechmatics.mdx b/fern/providers/transcriber/speechmatics.mdx index 8b3eb82ae..a646d774d 100644 --- a/fern/providers/transcriber/speechmatics.mdx +++ b/fern/providers/transcriber/speechmatics.mdx @@ -72,23 +72,29 @@ The following language values are currently accepted by Vapi for this provider. | Language | Language code | | --- | --- | -| Automatic detection | `auto` | | Arabic | `ar` | | Arabic and English | `ar_en` | +| Automatic detection | `auto` | +| Bangla | `bn` | | Bashkir | `ba` | | Basque | `eu` | | Belarusian | `be` | -| Bangla | `bn` | | Bulgarian | `bg` | | Cantonese | `yue` | | Catalan | `ca` | +| Chinese | `cmn` | +| Chinese and English | `cmn_en` | | Croatian | `hr` | | Czech | `cs` | | Danish | `da` | | Dutch | `nl` | | English | `en` | +| English and Malay | `en_ms` | +| English and Spanish | `en_es` | +| English and Tamil | `en_ta` | | Esperanto | `eo` | | Estonian | `et` | +| Filipino | `tl` | | Finnish | `fi` | | French | `fr` | | Galician | `gl` | @@ -106,10 +112,7 @@ The following language values are currently accepted by Vapi for this provider. | Latvian | `lv` | | Lithuanian | `lt` | | Malay | `ms` | -| English and Malay | `en_ms` | | Maltese | `mt` | -| Chinese | `cmn` | -| Chinese and English | `cmn_en` | | Marathi | `mr` | | Mongolian | `mn` | | Norwegian | `no` | @@ -121,12 +124,9 @@ The following language values are currently accepted by Vapi for this provider. | Slovak | `sk` | | Slovenian | `sl` | | Spanish | `es` | -| English and Spanish | `en_es` | | Swahili | `sw` | | Swedish | `sv` | -| Filipino | `tl` | | Tamil | `ta` | -| English and Tamil | `en_ta` | | Thai | `th` | | Turkish | `tr` | | Ukrainian | `uk` | diff --git a/fern/providers/transcriber/talkscriber.mdx b/fern/providers/transcriber/talkscriber.mdx index b032ebd8c..d82940388 100644 --- a/fern/providers/transcriber/talkscriber.mdx +++ b/fern/providers/transcriber/talkscriber.mdx @@ -5,109 +5,6 @@ description: Use Talkscriber with Vapi for real-time Whisper transcription. See slug: providers/transcriber/talkscriber --- -{/* Legacy marketing copy retained temporarily during provider-page standardization. - -**What is Talkscriber?** - -Talkscriber is an advanced AI-powered speech-to-text platform designed to deliver high-accuracy transcription and emotion detection. Focused on enterprise-grade solutions, Talkscriber provides secure, cost-effective, and flexible deployment options. This platform enhances business operations by converting spoken language into text and analyzing customer interactions for deeper insights. - -**The Evolution of Speech-to-Text:** - -Speech-to-text technology has significantly evolved, from basic voice recognition to sophisticated AI-driven transcription systems. Innovations in machine learning and natural language processing have paved the way for more accurate and efficient speech-to-text solutions. Talkscriber leverages these advancements to offer state-of-the-art transcription services that cater to modern enterprise needs. - -**Overview of Talkscriber’s Offerings:** - -Talkscriber offers a suite of AI-driven tools designed to support various applications: - -**AI Transcription:** - -Talkscriber’s core service is its AI-powered transcription technology, which converts spoken language into text with high accuracy. This technology supports multiple languages and dialects, making it versatile for global applications. - -**Emotion Detection:** - -Talkscriber includes advanced emotion detection capabilities, identifying emotions such as anger, joy, sadness, and surprise. This feature provides deeper insights into customer interactions and helps businesses understand their clients better. - -**API:** - -Talkscriber provides a robust API that allows developers to integrate its speech-to-text capabilities into their applications, ensuring low latency and high availability. - -**AI Transcription Technology:** - -Talkscriber’s AI transcription technology offers several key features and benefits: - -**Features:** - -- High Accuracy: Industry-leading transcription accuracy with a Word Error Rate (WER) under 4%. -- Real-time Transcription: Instantaneous conversion of speech to text. -- Multilingual Support: Supports multiple languages and dialects. - -**Benefits:** - -- Efficiency: Reduces the time needed to transcribe and analyze speech. -- Scalability: Handles large volumes of data efficiently. -- Cost-Effective: Provides high performance at a lower cost compared to other solutions. - -**Emotion and Intent Detection:** - -Talkscriber’s emotion detection capabilities enhance the analysis of customer interactions: - -**Enhancing Interaction Analysis:** - -- Emotion Detection: Identifies emotions at the utterance level, providing deeper insights. -- Purchase Intent Detection: Recognizes customer purchase intent, helping businesses tailor their strategies. - -**Developer API:** - -Talkscriber offers a comprehensive API for easy integration of their capabilities into various applications: - - -**Integration:** - -- SDKs: Available for multiple programming languages. -- Comprehensive Documentation: Detailed guides and support for seamless implementation. - -**Use Cases:** - -- Business Solutions: Enhance operational efficiency and customer service. -- Market Research: Gain insights into customer behavior and preferences. - - -**Use Cases for Talkscriber:** - -Talkscriber’s platform supports a wide range of applications across various sectors: - -**Business Solutions:** - -Improve business operations with accurate transcription and emotion detection. - - -**Customer Service:** - -Enhance customer service by understanding and responding to customer emotions and intents. - - -**Market Research:** - -Gain valuable insights into market trends and customer preferences through advanced speech analysis. - -**Impact on Business Operations:** - -Talkscriber is revolutionizing business operations by providing tools that enhance productivity and insights. By automating transcription and emotion detection, businesses can focus on innovation and strategy rather than manual processes. - -**Innovation and Research:** - -Talkscriber is committed to continuous innovation and research in speech AI. Their team of experts focuses on advancing the capabilities of AI transcription and emotion detection, exploring new applications, and refining existing technologies to stay at the forefront of the industry. - -**AI Safety and Ethics:** - -Ensuring the ethical use of AI is a core principle at Talkscriber. They implement robust safeguards to prevent misuse of their technology and are actively involved in promoting responsible AI development. Protecting user data and maintaining transparency in AI operations are central to their mission. - -**Integrations and Compatibility:** - -Talkscriber’s API allows seamless integration with various platforms and applications. This ensures that users can incorporate Talkscriber’s AI capabilities into their existing systems effortlessly, enhancing functionality and improving user experience. - -*/} - Talkscriber provides real-time speech-to-text over a streaming WebSocket connection. In Vapi, Talkscriber uses the Whisper model to turn the caller's audio into transcripts for the assistant. ## Speech-to-text @@ -145,108 +42,110 @@ Set `transcriber.language` to the language spoken by the caller. Providing the e ### Supported languages +The following languages are included in [Talkscriber's supported language list](https://docs.talkscriber.com/docs/appendix/) and accepted by Vapi. + | Language | Language code | | --- | --- | -| English | `en` | -| Chinese | `zh` | -| German | `de` | -| Spanish | `es` | -| Russian | `ru` | -| Korean | `ko` | -| French | `fr` | -| Japanese | `ja` | -| Portuguese | `pt` | -| Turkish | `tr` | -| Polish | `pl` | +| Afrikaans | `af` | +| Albanian | `sq` | +| Amharic | `am` | +| Arabic | `ar` | +| Armenian | `hy` | +| Assamese | `as` | +| Azerbaijani | `az` | +| Bashkir | `ba` | +| Basque | `eu` | +| Belarusian | `be` | +| Bengali | `bn` | +| Bosnian | `bs` | +| Breton | `br` | +| Bulgarian | `bg` | +| Cantonese | `yue` | | Catalan | `ca` | +| Chinese | `zh` | +| Croatian | `hr` | +| Czech | `cs` | +| Danish | `da` | | Dutch | `nl` | -| Arabic | `ar` | -| Swedish | `sv` | -| Italian | `it` | -| Indonesian | `id` | -| Hindi | `hi` | +| English | `en` | +| Estonian | `et` | +| Faroese | `fo` | | Finnish | `fi` | -| Vietnamese | `vi` | -| Hebrew | `he` | -| Ukrainian | `uk` | +| French | `fr` | +| Galician | `gl` | +| Georgian | `ka` | +| German | `de` | | Greek | `el` | -| Malay | `ms` | -| Czech | `cs` | -| Romanian | `ro` | -| Danish | `da` | +| Gujarati | `gu` | +| Haitian Creole | `ht` | +| Hausa | `ha` | +| Hawaiian | `haw` | +| Hebrew | `he` | +| Hindi | `hi` | | Hungarian | `hu` | -| Tamil | `ta` | -| Norwegian | `no` | -| Thai | `th` | -| Urdu | `ur` | -| Croatian | `hr` | -| Bulgarian | `bg` | -| Lithuanian | `lt` | +| Icelandic | `is` | +| Indonesian | `id` | +| Italian | `it` | +| Japanese | `ja` | +| Javanese | `jw` | +| Kannada | `kn` | +| Kazakh | `kk` | +| Khmer | `km` | +| Korean | `ko` | +| Lao | `lo` | | Latin | `la` | -| Maori | `mi` | -| Malayalam | `ml` | -| Welsh | `cy` | -| Slovak | `sk` | -| Telugu | `te` | -| Persian | `fa` | | Latvian | `lv` | -| Bengali | `bn` | -| Serbian | `sr` | -| Azerbaijani | `az` | -| Slovenian | `sl` | -| Kannada | `kn` | -| Estonian | `et` | +| Lingala | `ln` | +| Lithuanian | `lt` | +| Luxembourgish | `lb` | | Macedonian | `mk` | -| Breton | `br` | -| Basque | `eu` | -| Icelandic | `is` | -| Armenian | `hy` | -| Nepali | `ne` | -| Mongolian | `mn` | -| Bosnian | `bs` | -| Kazakh | `kk` | -| Albanian | `sq` | -| Swahili | `sw` | -| Galician | `gl` | +| Malagasy | `mg` | +| Malay | `ms` | +| Malayalam | `ml` | +| Maltese | `mt` | +| Maori | `mi` | | Marathi | `mr` | -| Punjabi | `pa` | -| Sinhala | `si` | -| Khmer | `km` | -| Shona | `sn` | -| Yoruba | `yo` | -| Somali | `so` | -| Afrikaans | `af` | +| Mongolian | `mn` | +| Myanmar (Burmese) | `my` | +| Nepali | `ne` | +| Norwegian | `no` | +| Norwegian Nynorsk | `nn` | | Occitan | `oc` | -| Georgian | `ka` | -| Belarusian | `be` | -| Tajik | `tg` | -| Sindhi | `sd` | -| Gujarati | `gu` | -| Amharic | `am` | -| Yiddish | `yi` | -| Lao | `lo` | -| Uzbek | `uz` | -| Faroese | `fo` | -| Haitian Creole | `ht` | | Pashto | `ps` | -| Turkmen | `tk` | -| Norwegian Nynorsk | `nn` | -| Maltese | `mt` | +| Persian | `fa` | +| Polish | `pl` | +| Portuguese | `pt` | +| Punjabi | `pa` | +| Romanian | `ro` | +| Russian | `ru` | | Sanskrit | `sa` | -| Luxembourgish | `lb` | -| Myanmar (Burmese) | `my` | -| Tibetan | `bo` | +| Serbian | `sr` | +| Shona | `sn` | +| Sindhi | `sd` | +| Sinhala | `si` | +| Slovak | `sk` | +| Slovenian | `sl` | +| Somali | `so` | +| Spanish | `es` | +| Sundanese | `su` | +| Swahili | `sw` | +| Swedish | `sv` | | Tagalog | `tl` | -| Malagasy | `mg` | -| Assamese | `as` | +| Tajik | `tg` | +| Tamil | `ta` | | Tatar | `tt` | -| Hawaiian | `haw` | -| Lingala | `ln` | -| Hausa | `ha` | -| Bashkir | `ba` | -| Javanese | `jw` | -| Sundanese | `su` | -| Cantonese | `yue` | +| Telugu | `te` | +| Thai | `th` | +| Tibetan | `bo` | +| Turkish | `tr` | +| Turkmen | `tk` | +| Ukrainian | `uk` | +| Urdu | `ur` | +| Uzbek | `uz` | +| Vietnamese | `vi` | +| Welsh | `cy` | +| Yiddish | `yi` | +| Yoruba | `yo` | ## When to use Talkscriber diff --git a/fern/providers/voice/azure.mdx b/fern/providers/voice/azure.mdx index 1d2a91713..1ceeb13d8 100644 --- a/fern/providers/voice/azure.mdx +++ b/fern/providers/voice/azure.mdx @@ -140,6 +140,10 @@ curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \ For additional API configuration options, review the [`AzureVoice` fields](/api-reference/assistants/create#request.body.voice.AzureVoice) in the Create Assistant API reference. +## Supported languages + +Language is set by the voice you choose. Each Azure neural voice is tied to a specific locale, so selecting a `voiceId` determines the spoken language. There is no separate language setting for Azure text-to-speech. Browse voices by language and copy a `voiceId` from the [Voice Library](/providers/voice/overview). + ## Related diff --git a/fern/providers/voice/cartesia.mdx b/fern/providers/voice/cartesia.mdx index fee606847..87c9abde0 100644 --- a/fern/providers/voice/cartesia.mdx +++ b/fern/providers/voice/cartesia.mdx @@ -5,104 +5,6 @@ description: Configure Cartesia as your Vapi assistant's text-to-speech provider slug: providers/voice/cartesia --- -{/* Legacy marketing copy retained temporarily during provider-page standardization. - -**What is Cartesia.ai?** - -Cartesia.ai is an advanced AI platform dedicated to developing real-time multimodal intelligence that operates across various devices. Specializing in ultrafast, realistic speech synthesis and voice API solutions, Cartesia.ai combines state-of-the-art AI technology with practical applications, empowering users to create high-quality, interactive voice content efficiently. - -**The Evolution of Multimodal AI:** - -AI technology has evolved from single-modal applications to sophisticated multimodal systems capable of processing and generating text, audio, video, and images. These advancements have paved the way for more integrated and interactive AI solutions. Cartesia.ai leverages these developments to offer comprehensive AI services that cater to diverse needs. - -**Overview of Cartesia.ai’s Offerings:** - -Cartesia.ai provides a range of AI-driven tools designed to support various applications: - -**Real-time Voice API:** - -Cartesia.ai’s real-time voice API is engineered for speed and efficiency, offering low latency and high-quality voice generation. This makes it ideal for applications requiring immediate feedback, such as virtual assistants, interactive games, and live conversations. - -**Multimodal Intelligence:** - -Cartesia.ai’s multimodal intelligence capabilities extend beyond voice synthesis, encompassing text, audio, video, and images. This enables users to create more interactive and engaging content by integrating multiple forms of media into a single platform. - -**Ultrafast Voice Synthesis:** - -Cartesia.ai’s ultrafast voice synthesis technology offers several key features and benefits: - -**Features:** - -- Low Latency Streaming: Ensures quick response times for real-time applications. -- High Availability: Delivers reliable performance even under heavy loads. -- Expressive Voices: Provides a wide range of emotions and nuances, enhancing the naturalness of generated speech. - -**Benefits:** - -- Engagement: Enhances user interactions with immediate and natural responses. -- Scalability: Manages large volumes of requests without compromising quality. -- Versatility: Suitable for various applications, from customer service to entertainment. - -**Multimodal Intelligence:** - -Cartesia.ai’s multimodal intelligence capabilities provide comprehensive solutions for creating interactive and engaging content: - -Text, Audio, Video, Images - -- Integrated Media: Combine text, audio, video, and images for more immersive experiences. -- Advanced AI Models: Utilize state-of-the-art AI models for high-quality media processing. - -**Developer API:** - -Cartesia.ai offers a robust API with comprehensive documentation and SDKs, facilitating seamless integration: - -**Integration:** - -- SDKs: Available for multiple programming languages. -- Low Latency: Supports real-time applications with quick response times. -- Documentation: Detailed guides and support for easy implementation. - -**Use Cases:** - -- Interactive Applications: Real-time voice generation for chatbots and virtual assistants. -- On-demand Voice Generation: Seamlessly integrate into content creation workflows. - -**Use Cases for Cartesia.ai:** - -Cartesia.ai’s versatile platform supports a wide range of applications: - -**Marketing:** - -Create engaging marketing content with high-quality voiceovers, transforming scripts into professional audio quickly and efficiently. - - -**Real-time Applications:** - -Build real-time conversational experiences with ultrafast voice synthesis, ensuring every interaction is instant and engaging. - - -**Content Creation:** - -Simplify content creation and produce high-quality audio for videos and other media at scale, reducing the time and effort required for traditional recording methods. - -**Impact on Content Creation:** - -Cartesia.ai is revolutionizing content creation by providing tools that enhance productivity and engagement. By automating voice generation and integrating multimodal intelligence, creators can focus on producing high-quality content without the time-consuming task of manual media creation. This boosts productivity and allows for greater creative freedom and innovation. - -**Innovation and Research:** - -Cartesia.ai is committed to continuous innovation and research in AI technology. Their team of experts focuses on advancing the capabilities of multimodal AI, exploring new applications, and refining existing technologies to stay at the forefront of the industry. - -**AI Safety and Ethics:** - -Ensuring the ethical use of AI is a core principle at Cartesia.ai. They implement robust safeguards to prevent misuse of their technology and are actively involved in promoting responsible AI development. Protecting user data and maintaining transparency in AI operations are central to their mission. - -**Integrations and Compatibility:** - -Cartesia.ai’s API allows seamless integration with various platforms and applications. This ensures that users can incorporate Cartesia.ai’s AI capabilities into their existing systems effortlessly, enhancing functionality and improving user experience. - -*/} - Cartesia provides text-to-speech for Vapi voice agents. You can use Cartesia through Vapi's default integration, or connect your own account in [Integrations](/providers/integrations). @@ -115,67 +17,89 @@ You can use Cartesia through Vapi's default integration, or connect your own acc ## Text-to-speech -Set `voice.provider` to `cartesia` and `voice.voiceId` to a voice. Cartesia offers many voices and supports voice cloning, you can browse and copy a voice's ID from the [Voice Library](/providers/voice/overview). +Set `voice.provider` to `cartesia` and `voice.voiceId` to a voice. `voice.model` is optional because Vapi selects the appropriate model for the voice ID when you omit it. To select a model explicitly, use one of the supported model IDs below. + +Cartesia offers many voices and supports voice cloning. You can browse and copy a voice's ID from the [Voice Library](/providers/voice/overview). ```bash curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \ -H "Authorization: Bearer $VAPI_API_KEY" \ -H "Content-Type: application/json" \ -d '{ - "voice": { "provider": "cartesia", "voiceId": "VOICE_ID" } + "voice": { + "provider": "cartesia", + "model": "sonic-3.5", + "voiceId": "VOICE_ID" + } }' ``` For additional API configuration options, review the [`CartesiaVoice` fields](/api-reference/assistants/create#request.body.voice.CartesiaVoice) in the Create Assistant API reference. -### Supported languages - -The following language codes are currently accepted by Vapi for this capability. +### Supported models -| Language | Language code | +| Model | Model ID | | --- | --- | -| Arabic | `ar` | -| Bulgarian | `bg` | -| Bangla | `bn` | -| Czech | `cs` | -| Danish | `da` | -| German | `de` | -| Greek | `el` | -| English | `en` | -| Spanish | `es` | -| Finnish | `fi` | -| French | `fr` | -| Gujarati | `gu` | -| Hebrew | `he` | -| Hindi | `hi` | -| Croatian | `hr` | -| Hungarian | `hu` | -| Indonesian | `id` | -| Italian | `it` | -| Japanese | `ja` | -| Georgian | `ka` | -| Kannada | `kn` | -| Korean | `ko` | -| Malayalam | `ml` | -| Marathi | `mr` | -| Malay | `ms` | -| Dutch | `nl` | -| Norwegian | `no` | -| Punjabi | `pa` | -| Polish | `pl` | -| Portuguese | `pt` | -| Romanian | `ro` | -| Russian | `ru` | -| Slovak | `sk` | -| Swedish | `sv` | -| Tamil | `ta` | -| Telugu | `te` | -| Thai | `th` | -| Filipino | `tl` | -| Turkish | `tr` | -| Ukrainian | `uk` | -| Vietnamese | `vi` | -| Chinese | `zh` | +| Sonic 3.5 | `sonic-3.5` | +| Sonic 3.5 (May 4, 2026 snapshot) | `sonic-3.5-2026-05-04` | +| Sonic 3 | `sonic-3` | +| Sonic 3 (January 12, 2026 snapshot) | `sonic-3-2026-01-12` | +| Sonic 3 (October 27, 2025 snapshot) | `sonic-3-2025-10-27` | +| Sonic 2 | `sonic-2` | +| Sonic 2 (June 11, 2025 snapshot) | `sonic-2-2025-06-11` | +| Sonic English | `sonic-english` | +| Sonic Multilingual | `sonic-multilingual` | +| Sonic Preview | `sonic-preview` | +| Sonic | `sonic` | + +### Supported languages + +Language support depends on the selected model. The following model and language combinations are currently supported by Vapi. Dated snapshot models (for example, `sonic-3-2026-01-12`) match their base model's language coverage. + +| Language | Language code | Sonic 3.5 / Sonic 3 | Sonic 2 / Sonic / Sonic Multilingual | Sonic English / Sonic Preview | +| --- | --- | --- | --- | --- | +| Arabic | `ar` | X | | | +| Bangla | `bn` | X | | | +| Bulgarian | `bg` | X | | | +| Chinese | `zh` | X | X | | +| Croatian | `hr` | X | | | +| Czech | `cs` | X | | | +| Danish | `da` | X | | | +| Dutch | `nl` | X | X | | +| English | `en` | X | X | X | +| Filipino | `tl` | X | | | +| Finnish | `fi` | X | | | +| French | `fr` | X | X | | +| Georgian | `ka` | X | | | +| German | `de` | X | X | | +| Greek | `el` | X | | | +| Gujarati | `gu` | X | | | +| Hebrew | `he` | X | | | +| Hindi | `hi` | X | X | | +| Hungarian | `hu` | X | | | +| Indonesian | `id` | X | | | +| Italian | `it` | X | X | | +| Japanese | `ja` | X | X | | +| Kannada | `kn` | X | | | +| Korean | `ko` | X | X | | +| Malay | `ms` | X | | | +| Malayalam | `ml` | X | | | +| Marathi | `mr` | X | | | +| Norwegian | `no` | X | | | +| Polish | `pl` | X | X | | +| Portuguese | `pt` | X | X | | +| Punjabi | `pa` | X | | | +| Romanian | `ro` | X | | | +| Russian | `ru` | X | X | | +| Slovak | `sk` | X | | | +| Spanish | `es` | X | X | | +| Swedish | `sv` | X | X | | +| Tamil | `ta` | X | | | +| Telugu | `te` | X | | | +| Thai | `th` | X | | | +| Turkish | `tr` | X | X | | +| Ukrainian | `uk` | X | | | +| Vietnamese | `vi` | X | | | ## Related diff --git a/fern/providers/voice/elevenlabs.mdx b/fern/providers/voice/elevenlabs.mdx index f447e4df7..eed3dc22d 100644 --- a/fern/providers/voice/elevenlabs.mdx +++ b/fern/providers/voice/elevenlabs.mdx @@ -5,120 +5,6 @@ description: Configure ElevenLabs as your Vapi assistant's text-to-speech provid slug: providers/voice/elevenlabs --- -{/* Legacy marketing copy retained temporarily during provider-page standardization. - -# How Vapi Integrates Text-to-Speech Platforms: ElevenLabs - -In the realm of voice AI development, integrating cutting-edge text-to-speech (TTS) platforms is crucial for creating natural and engaging conversational experiences. This guide explores how developers can leverage our voice AI platform to seamlessly incorporate advanced TTS services like ElevenLabs, enabling the creation of sophisticated voice-driven applications with remarkable efficiency. - -## Understanding the Voice AI Platform - -Our platform serves as a comprehensive toolkit for developers, designed to simplify the complexities inherent in voice AI development. By abstracting intricate technical details, it allows developers to focus on crafting the core business logic of their applications rather than grappling with low-level implementation challenges. - -### Key Components of the Voice AI Architecture - -At the heart of our platform lies a robust architecture comprising three essential components: - -1. Automatic Speech Recognition (ASR) -2. Large Language Model (LLM) processing -3. Text-to-Speech (TTS) integration - -These components work in concert to facilitate seamless voice interactions. The ASR module captures and processes audio inputs, converting spoken words into digital data. The LLM processing unit analyzes this data, interpreting context and generating appropriate responses. Finally, the TTS integration transforms these responses back into natural-sounding speech. - -## Integration with Text-to-Speech Platforms - -Our approach to integrating external TTS services, such as ElevenLabs, is designed to be both flexible and powerful. By incorporating advanced TTS platforms, developers can significantly enhance the quality and versatility of their voice AI applications. - -### ElevenLabs Integration: A Technical Deep Dive - -The integration with ElevenLabs' AI speech synthesis exemplifies our commitment to providing developers with state-of-the-art tools. This integration process involves several key technical aspects: - -1. **API Integration**: Our platform seamlessly connects with ElevenLabs' API, allowing for efficient data exchange and real-time speech synthesis. - -2. **Voice Model Selection**: Developers can choose from a range of voice models provided by ElevenLabs, each with unique characteristics and tonal qualities. - -3. **Parameter Control**: Fine-tuning of speech parameters such as speed, pitch, and emphasis is made accessible through our intuitive interface. - -4. **Data Flow Optimization**: We've implemented efficient data handling mechanisms to ensure smooth transmission between our platform and ElevenLabs' servers, minimizing latency and maintaining high-quality output. - -## Advanced Features of the Integration - -The integration of ElevenLabs' technology brings forth a suite of advanced features that elevate the capabilities of voice AI applications. - -### Contextual Awareness in Speech Synthesis - -By leveraging ElevenLabs' sophisticated algorithms, our platform enables AI-generated speech that demonstrates a high degree of contextual awareness. This results in more natural-sounding conversations that can adapt to the nuances of different scenarios and user interactions. - -### Enhanced Voice Modulation and Emotional Expression - -The integration allows for precise control over voice modulation and emotional expression. Developers can craft AI voices that convey a wide range of emotions, from excitement to empathy, enhancing the overall user experience and making interactions more engaging and human-like. - -### Real-time Audio Streaming Capabilities - -One of the most compelling features of our integration is the ability to leverage ElevenLabs' streaming capabilities for real-time applications. This functionality is crucial for creating responsive voice AI systems that can engage in dynamic, live interactions. - -Implementing low-latency voice synthesis presents several technical challenges, including: - -- **Network Latency Management**: Minimizing delays in data transmission between our platform, ElevenLabs' servers, and the end-user's device. -- **Buffer Optimization**: Balancing audio quality with real-time performance through careful buffer management. -- **Adaptive Bitrate Streaming**: Implementing techniques to adjust audio quality based on network conditions, ensuring consistent performance across various environments. - -Our platform addresses these challenges through advanced streaming protocols and optimized data handling, enabling developers to create voice AI applications that respond with near-human speed and fluidity. - -## Developer Tools and Resources - -To facilitate the integration process, we provide a comprehensive set of developer tools and resources: - -- **SDKs**: Open-source software development kits available on GitHub, supporting multiple programming languages. -- **Documentation**: Detailed API references and conceptual guides covering key aspects of voice AI development. -- **Quickstart Guides**: Step-by-step tutorials to help developers get up and running quickly. -- **End-to-End Examples**: Sample implementations of common voice workflows, including outbound sales calls, inbound support interactions, and web-based voice interfaces. - -### Building Custom Voice AI Applications - -Developers can follow these steps to create voice AI applications with integrated TTS: - -1. **Define the Use Case**: Clearly outline the objectives and scope of the voice AI application. -2. **Select the Appropriate Voice Model**: Choose an ElevenLabs voice that aligns with the application's tone and purpose. -3. **Implement Core Logic**: Utilize our SDKs to implement the application's business logic and conversation flow. -4. **Configure TTS Parameters**: Fine-tune speech synthesis settings to achieve the desired voice characteristics. -5. **Test and Iterate**: Conduct thorough testing to ensure natural conversation flow and appropriate responses. -6. **Optimize Performance**: Leverage our platform's analytics tools to identify and address any performance bottlenecks. - -Best practices for optimizing voice AI performance and user experience include: - -- Implementing effective error handling and fallback mechanisms -- Designing clear and concise conversation flows -- Regularly updating and refining language models based on user interactions -- Optimizing for low-latency responses to maintain natural conversation cadence - -## Use Cases and Applications - -The integration of advanced TTS platforms opens up a myriad of possibilities across various industries: - -- **Customer Service**: Creating empathetic and efficient AI-powered support agents. -- **Education**: Developing interactive language learning tools with native-speaker quality pronunciation. -- **Healthcare**: Building voice-based assistants for patient engagement and medical information delivery. -- **Entertainment**: Crafting immersive storytelling experiences with dynamically generated character voices. - -Developers can leverage this integration to create unique voice-based solutions that were previously challenging or impossible to implement with traditional TTS technologies. - -## Future Developments and Potential - -As the field of voice AI continues to advance, our platform is poised to incorporate new features and improvements in TTS integration capabilities. Upcoming developments may include: - -- Enhanced multilingual support for global applications -- More sophisticated emotional intelligence in voice synthesis -- Improved personalization capabilities, allowing for voice adaptation based on user preferences - -The future of voice AI development is likely to see increased focus on natural language understanding, context-aware responses, and seamless multi-modal interactions. Our platform is well-positioned to address these trends, providing developers with the tools they need to stay at the forefront of voice technology innovation. - -## Conclusion - -The integration of advanced text-to-speech platforms like ElevenLabs into our voice AI development ecosystem represents a significant leap forward for developers seeking to create sophisticated, natural-sounding voice applications. By abstracting complex technical challenges and providing robust tools and resources, we enable developers to focus on innovation and creativity in their voice AI projects. As the technology continues to evolve, our platform will remain at the cutting edge, empowering developers to build the next generation of voice-driven experiences. - -*/} - ElevenLabs provides text-to-speech for Vapi voice agents. You can use ElevenLabs through Vapi's default integration, or connect your own account in [Integrations](/providers/integrations). @@ -131,19 +17,130 @@ You can use ElevenLabs through Vapi's default integration, or connect your own a ## Text-to-speech -Set `voice.provider` to `11labs` and `voice.voiceId` to a voice. ElevenLabs offers many voices and supports voice cloning, you can browse and copy a voice's ID from the [Voice Library](/providers/voice/overview); the default voice is `sarah`. +Set `voice.provider` to `11labs`, `voice.model` to a supported model, and `voice.voiceId` to a voice. ElevenLabs offers many voices and supports voice cloning. You can browse and copy a voice's ID from the [Voice Library](/providers/voice/overview); the default voice is `sarah`. ```bash curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \ -H "Authorization: Bearer $VAPI_API_KEY" \ -H "Content-Type: application/json" \ -d '{ - "voice": { "provider": "11labs", "voiceId": "sarah" } + "voice": { + "provider": "11labs", + "model": "eleven_flash_v2_5", + "voiceId": "sarah" + } }' ``` For additional API configuration options, review the [`ElevenLabsVoice` fields](/api-reference/assistants/create#request.body.voice.ElevenLabsVoice) in the Create Assistant API reference. +### Supported models + +| Model | Model ID | +| --- | --- | +| Eleven Flash v2 | `eleven_flash_v2` | +| Eleven Flash v2.5 | `eleven_flash_v2_5` | +| Eleven Multilingual v2 | `eleven_multilingual_v2` | +| Eleven v3 | `eleven_v3` | + +### Configuration options + +| Option | Accepted values | Description | +| --- | --- | --- | +| `stability` | `0` to `1` | Controls consistency between generations. | +| `similarityBoost` | `0` to `1` | Controls how closely the output matches the selected voice. | +| `style` | `0` to `1` | Controls style exaggeration. | +| `useSpeakerBoost` | `true` or `false` | Enables speaker similarity enhancement. | +| `speed` | `0.7` to `1.2` | Controls speaking speed. | +| `optimizeStreamingLatency` | `0` to `4` | Controls streaming-latency optimization. The default is `3`. | +| `enableSsmlParsing` | `true` or `false` | Enables supported SSML pronunciation syntax. The default is `false`. | +| `autoMode` | `true` or `false` | Enables automatic mode selection. The default is `false`. | + +### Supported languages + +ElevenLabs models infer the language from the text. Language coverage depends on the selected model. + +The following language coverage is published for models supported by Vapi. See [ElevenLabs models](https://elevenlabs.io/docs/overview/models) for provider details. + +| Language | Language code | Eleven Flash v2 | Eleven Flash v2.5 | Eleven Multilingual v2 | Eleven v3 | +| --- | --- | --- | --- | --- | --- | +| Afrikaans | `af` | | | | X | +| Arabic | `ar` | | X | X | X | +| Armenian | `hy` | | | | X | +| Assamese | `as` | | | | X | +| Azerbaijani | `az` | | | | X | +| Belarusian | `be` | | | | X | +| Bengali | `bn` | | | | X | +| Bosnian | `bs` | | | | X | +| Bulgarian | `bg` | | X | X | X | +| Catalan | `ca` | | | | X | +| Cebuano | | | | | X | +| Chichewa | `ny` | | | | X | +| Croatian | `hr` | | X | X | X | +| Czech | `cs` | | X | X | X | +| Danish | `da` | | X | X | X | +| Dutch | `nl` | | X | X | X | +| English | `en` | X | X | X | X | +| Estonian | `et` | | | | X | +| Filipino | | | X | X | X | +| Finnish | `fi` | | X | X | X | +| French | `fr` | | X | X | X | +| Galician | `gl` | | | | X | +| Georgian | `ka` | | | | X | +| German | `de` | | X | X | X | +| Greek | `el` | | X | X | X | +| Gujarati | `gu` | | | | X | +| Hausa | `ha` | | | | X | +| Hebrew | `he` | | | | X | +| Hindi | `hi` | | X | X | X | +| Hungarian | `hu` | | X | | X | +| Icelandic | `is` | | | | X | +| Indonesian | `id` | | X | X | X | +| Irish | `ga` | | | | X | +| Italian | `it` | | X | X | X | +| Japanese | `ja` | | X | X | X | +| Javanese | `jv` | | | | X | +| Kannada | `kn` | | | | X | +| Kazakh | `kk` | | | | X | +| Kirghiz | `ky` | | | | X | +| Korean | `ko` | | X | X | X | +| Latvian | `lv` | | | | X | +| Lingala | `ln` | | | | X | +| Lithuanian | `lt` | | | | X | +| Luxembourgish | `lb` | | | | X | +| Macedonian | `mk` | | | | X | +| Malay | `ms` | | X | X | X | +| Malayalam | `ml` | | | | X | +| Mandarin Chinese | `zh` | | X | X | X | +| Marathi | `mr` | | | | X | +| Nepali | `ne` | | | | X | +| Norwegian | `no` | | X | | X | +| Pashto | `ps` | | | | X | +| Persian | `fa` | | | | X | +| Polish | `pl` | | X | X | X | +| Portuguese | `pt` | | X | X | X | +| Punjabi | `pa` | | | | X | +| Romanian | `ro` | | X | X | X | +| Russian | `ru` | | X | X | X | +| Serbian | `sr` | | | | X | +| Sindhi | `sd` | | | | X | +| Slovak | `sk` | | X | X | X | +| Slovenian | `sl` | | | | X | +| Somali | `so` | | | | X | +| Spanish | `es` | | X | X | X | +| Swahili | `sw` | | | | X | +| Swedish | `sv` | | X | X | X | +| Tamil | `ta` | | X | X | X | +| Telugu | `te` | | | | X | +| Thai | `th` | | | | X | +| Turkish | `tr` | | X | X | X | +| Ukrainian | `uk` | | X | X | X | +| Urdu | `ur` | | | | X | +| Vietnamese | `vi` | | X | | X | +| Welsh | `cy` | | | | X | + +Set `voice.language` (an ISO 639-1 code) to enforce a specific language. Enforcement is supported only on Eleven Flash v2.5. For the other models you do not need to set a language code. They detect the language from the input text, and providing a code returns an error. + ## Related diff --git a/fern/providers/voice/hume.mdx b/fern/providers/voice/hume.mdx index 2e057f8eb..ea464634f 100644 --- a/fern/providers/voice/hume.mdx +++ b/fern/providers/voice/hume.mdx @@ -28,6 +28,10 @@ curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \ For additional API configuration options, review the [`HumeVoice` fields](/api-reference/assistants/create#request.body.voice.HumeVoice) in the Create Assistant API reference. +## Supported languages + +Hume text-to-speech has no separate language setting. Language is determined by the selected voice, and the Hume voices currently available in Vapi are English. + ## Related diff --git a/fern/providers/voice/imnt.mdx b/fern/providers/voice/imnt.mdx index cbe213aef..6724d6e14 100644 --- a/fern/providers/voice/imnt.mdx +++ b/fern/providers/voice/imnt.mdx @@ -5,325 +5,76 @@ description: Configure an LMNT voice for a Vapi assistant and find its voice ID slug: providers/voice/imnt --- -{/* Legacy marketing copy retained temporarily during provider-page standardization. - -**What is LMNT?** - -LMNT is a cutting-edge AI platform that specializes in ultrafast and lifelike speech synthesis. By leveraging advanced AI technology, LMNT offers solutions for creating high-quality, natural-sounding speech from text. Their innovative voice cloning technology allows users to generate studio-quality voice replicas with minimal input, transforming the way businesses and developers create and use voice content. - -**The Evolution of AI Speech Synthesis:** - -AI speech synthesis has come a long way from its early, rudimentary forms to the sophisticated, lifelike voices we have today. Advances in deep learning, neural networks, and data processing have enabled the creation of speech that is virtually indistinguishable from human voices. LMNT has harnessed these advancements to provide fast, reliable, and highly expressive speech synthesis solutions. - -**Overview of LMNT’s Offerings:** - -LMNT provides a range of AI-driven speech synthesis tools designed to meet diverse needs: - -**Ultrafast Speech Synthesis:** - -- LMNT’s speech synthesis technology is designed for speed and efficiency, delivering low latency streaming that is ideal for conversational applications, virtual agents, and interactive games. This technology ensures that every interaction is immediate and engaging, enhancing user experience and operational efficiency. - - -**Voice Cloning:** - -- LMNT offers advanced voice cloning capabilities, allowing users to create lifelike and expressive voice replicas with as little as a 5-minute recording. Instant voice clones can be generated from just 15 seconds of audio. Users can also choose from a library of pre-built voices, making it easy to find the perfect match for any project. - -**Developer API:** - -- LMNT provides a robust API with SDKs for Python and Node.js, enabling seamless integration of their voice synthesis capabilities into various applications. The API supports ultrafast, low-latency streaming, making it perfect for real-time voice generation and playback scenarios. Comprehensive documentation and support are available to assist developers through every step of the integration process. - -**Ultrafast Speech Synthesis:** - -- LMNT’s ultrafast speech synthesis technology offers several key features and benefits: - -**Features:** - -- Low Latency Streaming: Designed for real-time applications, ensuring quick response times. -- High Availability: Reliable performance under high loads, making it suitable for large-scale deployments. -- Expressive Voices: Capable of conveying a wide range of emotions and nuances, enhancing the naturalness of generated speech. - -**Benefits:** - -- Engagement: Immediate and natural interactions improve user engagement and satisfaction. -- Scalability: Handle large volumes of requests without compromising on performance or quality. -- Versatility: Suitable for a wide range of applications, from customer service to entertainment. - -**Voice Cloning:** - -- LMNT’s voice cloning technology sets a new standard in creating lifelike and expressive voices: - -**Creating Lifelike Voices:** - -- Studio-quality Cloning: Generate high-fidelity voice clones with minimal recording input. -- Instant Voice Cloning: Create usable voice clones from just a few seconds of audio. -- Voice Library: Access a diverse library of pre-built voices for immediate use. - -**Applications:** - -- Personalization: Create unique voices for digital assistants, characters, and branding. -- Content Creation: Generate consistent and professional voiceovers for videos, podcasts, and more. - -**Developer API:** - -- LMNT’s developer API simplifies the integration of voice synthesis capabilities into various projects: - -**Integration:** - -- SDKs: Ready-to-use SDKs for Python and Node.js. -- Low Latency: Real-time voice synthesis for interactive applications. -- Documentation: Comprehensive guides and support for easy implementation. - -**Use Cases:** - -- Interactive Applications: Real-time voice generation for chatbots and virtual assistants. -- On-demand Voice Generation: Seamless integration into content creation workflows. - -**Use Cases for LMNT:** - -- LMNT’s versatile platform supports a wide range of applications: - -**Marketing:** - -Create engaging product marketing videos with captivating voiceovers, turning scripts into high-quality audio content quickly and efficiently. - -**Real-time Conversations:** - -Build lightning-fast conversational experiences with ultrafast speech synthesis, ensuring every interaction is instant and engaging. - -**Content Creation:** - -Simplify content creation and produce high-quality audio for videos and avatars at scale, reducing the time and effort required for traditional recording methods. - -**Impact on Content Creation:** - -LMNT is revolutionizing content creation by providing tools that enhance productivity and engagement. By automating voice generation, creators can focus on producing high-quality content without the time-consuming task of manual voice recording. This not only boosts productivity but also allows for more creative freedom and innovation. - -**Innovation and Research:** - -LMNT is committed to continuous innovation and research in the field of AI speech synthesis. Their team of experts is dedicated to improving the naturalness, expressiveness, and versatility of AI-generated voices. By exploring new applications and refining existing technologies, LMNT aims to stay at the forefront of the industry. - -**AI Safety and Ethics:** - -Ensuring the ethical use of AI is a core principle at LMNT. They implement robust safeguards to prevent misuse of their technology and are actively involved in promoting responsible AI development. Protecting user data and maintaining transparency in AI operations are central to their mission. - -**Integrations and Compatibility:** - -LMNT’s API allows seamless integration with various platforms and applications. This ensures that users can incorporate LMNT’s voice synthesis capabilities into their existing systems effortlessly, enhancing functionality and improving user experience. - -*/} - LMNT provides streaming text-to-speech voices for Vapi assistants, including voices from its catalog and supported cloned voices. You can use LMNT through Vapi's default integration, or use your own LMNT account by connecting it in [Integrations](/providers/integrations). ## Text-to-speech -Set `voice.provider` to `lmnt` and `voice.voiceId` to a voice. LMNT offers many voices and supports voice cloning, you can browse and copy a voice's ID from the [Voice Library](/providers/voice/overview); the default voice is `morgan`. +Set `voice.provider` to `lmnt` and `voice.voiceId` to a voice. LMNT offers many voices and supports voice cloning. You can browse and copy a voice's ID from the [Voice Library](/providers/voice/overview); the default voice is `morgan`. ```bash curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \ -H "Authorization: Bearer $VAPI_API_KEY" \ -H "Content-Type: application/json" \ -d '{ - "voice": { "provider": "lmnt", "voiceId": "morgan" } + "voice": { + "provider": "lmnt", + "voiceId": "morgan", + "language": "auto" + } }' ``` For additional API configuration options, review the [`LMNTVoice` fields](/api-reference/assistants/create#request.body.voice.LMNTVoice) in the Create Assistant API reference. +### Configuration options + +| Option | Accepted values | Description | +| --- | --- | --- | +| `voiceId` | LMNT voice ID | Selects a preset, shared, or cloned LMNT voice. | +| `language` | Supported language code or `auto` | Selects a language or enables automatic detection. | +| `speed` | `0.25` to `2` | Controls speaking speed. | + ### Supported languages Set `voice.language` to `auto` to automatically detect the language, or use one of the supported language codes below. -The following language values are currently accepted by Vapi for this provider. +The following languages are included in [LMNT's supported language catalog](https://docs.lmnt.com/build-with-lmnt/languages) and accepted by Vapi. | Language | Language code | | --- | --- | -| Afar | `aa` | -| Abkhazian | `ab` | -| Avestan | `ae` | -| Afrikaans | `af` | -| Akan | `ak` | -| Amharic | `am` | -| Aragonese | `an` | | Arabic | `ar` | | Assamese | `as` | -| Avaric | `av` | -| Aymara | `ay` | -| Azerbaijani | `az` | -| Bashkir | `ba` | -| Belarusian | `be` | -| Bulgarian | `bg` | -| Bhojpuri | `bh` | -| Bislama | `bi` | -| Bambara | `bm` | -| Bangla | `bn` | -| Tibetan | `bo` | -| Breton | `br` | -| Bosnian | `bs` | -| Catalan | `ca` | -| Chechen | `ce` | -| Chamorro | `ch` | -| Corsican | `co` | -| Cree | `cr` | +| Bengali | `bn` | +| Chinese | `zh` | | Czech | `cs` | -| Church Slavic | `cu` | -| Chuvash | `cv` | -| Welsh | `cy` | | Danish | `da` | -| German | `de` | -| Divehi | `dv` | -| Dzongkha | `dz` | -| Ewe | `ee` | -| Greek | `el` | +| Dutch | `nl` | | English | `en` | -| Esperanto | `eo` | -| Spanish | `es` | -| Estonian | `et` | -| Basque | `eu` | -| Persian | `fa` | -| Fula | `ff` | | Finnish | `fi` | -| Fijian | `fj` | -| Faroese | `fo` | | French | `fr` | -| Western Frisian | `fy` | -| Irish | `ga` | -| Scottish Gaelic | `gd` | -| Galician | `gl` | -| Guarani | `gn` | -| Gujarati | `gu` | -| Manx | `gv` | -| Hausa | `ha` | -| Hebrew | `he` | +| German | `de` | | Hindi | `hi` | -| Hiri Motu | `ho` | -| Croatian | `hr` | -| Haitian Creole | `ht` | -| Hungarian | `hu` | -| Armenian | `hy` | -| Herero | `hz` | -| Interlingua | `ia` | | Indonesian | `id` | -| Interlingue | `ie` | -| Igbo | `ig` | -| Sichuan Yi | `ii` | -| Inupiaq | `ik` | -| Ido | `io` | -| Icelandic | `is` | | Italian | `it` | -| Inuktitut | `iu` | | Japanese | `ja` | -| Javanese | `jv` | -| Georgian | `ka` | -| Kongo | `kg` | -| Kikuyu | `ki` | -| Kuanyama | `kj` | -| Kazakh | `kk` | -| Kalaallisut | `kl` | -| Khmer | `km` | -| Kannada | `kn` | | Korean | `ko` | -| Kanuri | `kr` | -| Kashmiri | `ks` | -| Kurdish | `ku` | -| Komi | `kv` | -| Cornish | `kw` | -| Kyrgyz | `ky` | -| Latin | `la` | -| Luxembourgish | `lb` | -| Ganda | `lg` | -| Limburgish | `li` | -| Lingala | `ln` | -| Lao | `lo` | -| Lithuanian | `lt` | -| Luba-Katanga | `lu` | -| Latvian | `lv` | -| Malagasy | `mg` | -| Marshallese | `mh` | -| Māori | `mi` | -| Macedonian | `mk` | | Malayalam | `ml` | -| Mongolian | `mn` | | Marathi | `mr` | -| Malay | `ms` | -| Maltese | `mt` | -| Burmese | `my` | -| Nauru | `na` | -| Norwegian Bokmål | `nb` | -| North Ndebele | `nd` | -| Nepali | `ne` | -| Ndonga | `ng` | -| Dutch | `nl` | -| Norwegian Nynorsk | `nn` | -| Norwegian | `no` | -| South Ndebele | `nr` | -| Navajo | `nv` | -| Nyanja | `ny` | -| Occitan | `oc` | -| Ojibwa | `oj` | -| Oromo | `om` | -| Odia | `or` | -| Ossetic | `os` | -| Punjabi | `pa` | -| Pali | `pi` | | Polish | `pl` | -| Pashto | `ps` | | Portuguese | `pt` | -| Quechua | `qu` | -| Romansh | `rm` | -| Rundi | `rn` | -| Romanian | `ro` | | Russian | `ru` | -| Kinyarwanda | `rw` | -| Sanskrit | `sa` | -| Sardinian | `sc` | -| Sindhi | `sd` | -| Northern Sami | `se` | -| Sango | `sg` | -| Sinhala | `si` | | Slovak | `sk` | -| Slovenian | `sl` | -| Samoan | `sm` | -| Shona | `sn` | -| Somali | `so` | -| Albanian | `sq` | -| Serbian | `sr` | -| Swati | `ss` | -| Southern Sotho | `st` | -| Sundanese | `su` | +| Spanish | `es` | | Swedish | `sv` | -| Swahili | `sw` | | Tamil | `ta` | | Telugu | `te` | -| Tajik | `tg` | | Thai | `th` | -| Tigrinya | `ti` | -| Turkmen | `tk` | -| Filipino | `tl` | -| Tswana | `tn` | -| Tongan | `to` | | Turkish | `tr` | -| Tsonga | `ts` | -| Tatar | `tt` | -| Akan | `tw` | -| Tahitian | `ty` | -| Uyghur | `ug` | | Ukrainian | `uk` | | Urdu | `ur` | -| Uzbek | `uz` | -| Venda | `ve` | | Vietnamese | `vi` | -| Volapük | `vo` | -| Walloon | `wa` | -| Wolof | `wo` | -| Xhosa | `xh` | -| Yiddish | `yi` | -| Cantonese | `yue` | -| Yoruba | `yo` | -| Zhuang | `za` | -| Chinese | `zh` | -| Zulu | `zu` | ## Related diff --git a/fern/providers/voice/inworld.mdx b/fern/providers/voice/inworld.mdx index d153a10d5..1a9a79f23 100644 --- a/fern/providers/voice/inworld.mdx +++ b/fern/providers/voice/inworld.mdx @@ -1,63 +1,76 @@ --- title: Inworld subtitle: Use Inworld text-to-speech voices with your Vapi voice agent. -description: Configure an Inworld voice for a Vapi assistant and find its voice ID in the Vapi Voice Library. +description: Configure Inworld text-to-speech models, voices, languages, and synthesis options for a Vapi assistant. slug: providers/voice/inworld --- -{/* Legacy marketing copy retained temporarily during provider-page standardization. - -**What is Inworld?** - -Inworld develops AI products for builders of consumer applications, enabling scaled applications that grow into user needs and organically evolve through experience. This includes a text-to-speech service that makes state-of-the-art voice AI radically more accessible for developers. Inworld TTS is optimized for low-latency streaming, making it suitable for applications requiring immediate audio responses. - -**Overview of State-of-the-Art Inworld TTS:** - -Advancements in LLM-based speech models have significantly improved the quality of AI-generated speech. Inworld leverages these developments to deliver natural-sounding, emotionally expressive voices suitable for various applications, including virtual assistants, interactive games, and more. Inworld provides a comprehensive suite of features designed to meet diverse voice synthesis needs: - -- Real-Time Speech Synthesis: Inworld is engineered for real-time performance, delivering the first 2-second audio chunk in as few as 200ms. This responsiveness is critical for real-time applications such as conversational agents and interactive characters. -- Multilingual Support: Inworld supports 11 languages, including English, Spanish, French, Korean, Chinese, and more. This multilingual capability enables developers to build applications for diverse global audiences. -- Developer API: Inworld provides an API with comprehensive documentation, facilitating integration into various applications. The API supports real-time streaming and offers options for customizing voice parameters to suit specific use cases. - -**Use Cases:** - -Inworld TTS supports a wide range of applications: - -- Interactive Applications: Developers can create responsive voice agents for customer service, virtual assistants, and interactive characters, enhancing user engagement through natural-sounding speech. -- Content Creation: Content creators can utilize Inworld to generate professional-grade voiceovers for videos, podcasts, and other media, streamlining the production process. -- Education and Training: Educational platforms can employ Inworld to provide clear and expressive narration for e-learning materials, improving the learning experience for users. - -**Integration with Vapi:** - -Inworld voices are fully integrated with Vapi, giving developers an easy way to deploy expressive, real-time latency voices in their assistants. - -To use Inworld voices, open your assistant in the Vapi dashboard and scroll to the Voice Configuration section. Choose Inworld as the provider, select a language and voice. Hit publish. And you’re live! - -**Conclusion:** - -Inworld offers a combination of expressive voice synthesis, real-time performance, and multilingual support, making it a valuable tool for developers seeking to enhance their applications with natural-sounding speech. - -*/} - Inworld provides streaming text-to-speech voices that you can use as a Vapi assistant's voice. You can use Inworld through Vapi's default integration, or use your own Inworld account by connecting it in [Integrations](/providers/integrations). ## Text-to-speech -Set `voice.provider` to `inworld` and `voice.voiceId` to a voice. Inworld offers many voices, you can browse and copy a voice's ID from the [Voice Library](/providers/voice/overview). +Set `voice.provider` to `inworld`, `voice.model` to a supported model, and `voice.voiceId` to a voice. Inworld offers many voices; browse and copy a voice's ID from the [Voice Library](/providers/voice/overview). ```bash curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \ -H "Authorization: Bearer $VAPI_API_KEY" \ -H "Content-Type: application/json" \ -d '{ - "voice": { "provider": "inworld", "voiceId": "VOICE_ID" } + "voice": { + "provider": "inworld", + "model": "inworld-tts-1.5-mini", + "voiceId": "Alex", + "languageCode": "en" + } }' ``` For additional API configuration options, review the [`InworldVoice` fields](/api-reference/assistants/create#request.body.voice.InworldVoice) in the Create Assistant API reference. +### Supported models + +The following non-deprecated Inworld model IDs are supported by Vapi. See [Inworld's model catalog](https://docs.inworld.ai/models) for provider details. + +| Model | Model ID | +| --- | --- | +| Realtime TTS 1.5 Max | `inworld-tts-1.5-max` | +| Realtime TTS 1.5 Mini | `inworld-tts-1.5-mini` | +| Realtime TTS-2 | `inworld-tts-2` | + +### Configuration options + +| Option | Accepted values | Description | +| --- | --- | --- | +| `voiceId` | Inworld voice ID | Selects an Inworld voice. | +| `model` | Supported model ID | Selects the text-to-speech model. | +| `languageCode` | Supported language code | Selects the synthesis language. The default is `en`. | +| `temperature` | `0.1` to `2` | Controls output variance. The default is `1.1`. | +| `speakingRate` | `0.5` to `1.5` | Controls speaking speed. The default is `1`. | + +### Supported languages + +Set `voice.languageCode` to one of the language codes below. Although Inworld offers additional language coverage for Realtime TTS-2, this table lists the languages currently accepted by Vapi. + +| Language | Language code | Realtime TTS 1.5 Max | Realtime TTS 1.5 Mini | Realtime TTS-2 | +| --- | --- | --- | --- | --- | +| Arabic | `ar` | X | X | X | +| Chinese | `zh` | X | X | X | +| Dutch | `nl` | X | X | X | +| English | `en` | X | X | X | +| French | `fr` | X | X | X | +| German | `de` | X | X | X | +| Hebrew | `he` | X | X | X | +| Hindi | `hi` | X | X | X | +| Italian | `it` | X | X | X | +| Japanese | `ja` | X | X | X | +| Korean | `ko` | X | X | X | +| Polish | `pl` | X | X | X | +| Portuguese | `pt` | X | X | X | +| Russian | `ru` | X | X | X | +| Spanish | `es` | X | X | X | + ## Related diff --git a/fern/providers/voice/microsoft.mdx b/fern/providers/voice/microsoft.mdx index d9c8b11d4..795c3d3b3 100644 --- a/fern/providers/voice/microsoft.mdx +++ b/fern/providers/voice/microsoft.mdx @@ -28,6 +28,10 @@ curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \ For additional API configuration options, review the [`MicrosoftVoice` fields](/api-reference/assistants/create#request.body.voice.MicrosoftVoice) in the Create Assistant API reference. +## Supported languages + +Language is set by the voice you choose. Each Microsoft voice is tied to a specific locale (for example, `en-US-Ethan:MAI-Voice-2`), so selecting a `voiceId` determines the spoken language. There is no separate language setting for Microsoft text-to-speech. Browse voices by language and copy a `voiceId` from the [Voice Library](/providers/voice/overview). + ## Related diff --git a/fern/providers/voice/minimax.mdx b/fern/providers/voice/minimax.mdx index e91d7bca6..45b6802a9 100644 --- a/fern/providers/voice/minimax.mdx +++ b/fern/providers/voice/minimax.mdx @@ -34,8 +34,6 @@ curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \ For additional API configuration options, review the [`MinimaxVoice` fields](/api-reference/assistants/create#request.body.voice.MinimaxVoice) in the Create Assistant API reference. -{/* verify: old voice page used model `speech-02-hd` and voiceId `Wise_Woman`; current code has `speech-02-turbo` active (speech-02-hd commented out) and default voice `socialmedia_female_1_v1`. */} - MiniMax offers many voices and supports voice cloning, you can browse and copy a voice's ID from the [Voice Library](/providers/voice/overview). The default voice is `socialmedia_female_1_v1`. ### Subtitle timing for live captions (`subtitleType`) @@ -84,6 +82,10 @@ If your use case requires word-by-word highlighting at audio playback cadence wi For the full event schema and `timing` shapes across all voice providers, see [Server events → Assistant Speech Started](/server-url/events#assistant-speech-started). +## Supported languages + +MiniMax has no separate language setting. Language comes from the selected voice and the input text. To prioritize a specific language during synthesis, optionally set `voice.languageBoost`. For the accepted `languageBoost` values, review the [`MinimaxVoice` fields](/api-reference/assistants/create#request.body.voice.MinimaxVoice) in the Create Assistant API reference. + ## Related diff --git a/fern/providers/voice/neuphonic.mdx b/fern/providers/voice/neuphonic.mdx index 92be6a12c..3f41dcab7 100644 --- a/fern/providers/voice/neuphonic.mdx +++ b/fern/providers/voice/neuphonic.mdx @@ -28,6 +28,19 @@ curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \ For additional API configuration options, review the [`NeuphonicVoice` fields](/api-reference/assistants/create#request.body.voice.NeuphonicVoice) in the Create Assistant API reference. +## Supported languages + +Set `voice.language` to a supported language. Neuphonic requires a language, and the available voices depend on it. + +| Language | Language code | +| --- | --- | +| Dutch | `nl` | +| English | `en` | +| English and Hindi | `en-hi` | +| German | `de` | +| Hindi | `hi` | +| Spanish | `es` | + ## Related diff --git a/fern/providers/voice/openai.mdx b/fern/providers/voice/openai.mdx index 17540e2d3..5a37aeae5 100644 --- a/fern/providers/voice/openai.mdx +++ b/fern/providers/voice/openai.mdx @@ -30,6 +30,10 @@ curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \ For additional API configuration options, review the [`OpenAIVoice` fields](/api-reference/assistants/create#request.body.voice.OpenAIVoice) in the Create Assistant API reference. +## Supported languages + +OpenAI text-to-speech has no separate language setting. The model speaks the language of the input text. + ## Related diff --git a/fern/providers/voice/overview.mdx b/fern/providers/voice/overview.mdx index ab6ed38fc..f4f39d1f0 100644 --- a/fern/providers/voice/overview.mdx +++ b/fern/providers/voice/overview.mdx @@ -7,28 +7,28 @@ slug: providers/voice/overview ## Supported voice providers -Every column reflects Vapi's coverage for that provider. The provider string is the exact value you pass in `voice.provider`. +The provider string is the exact value you pass in `voice.provider`. -| Provider | Provider string | HIPAA | GDPR (EU region) | PCI | -| -- | -- | -- | -- | -- | -| [Vapi Voices](/providers/voice/vapi-voices#text-to-speech) | `vapi` | Yes | No | Yes | -| [Azure](/providers/voice/azure#text-to-speech) | `azure` | Yes | No | Yes | -| [Cartesia](/providers/voice/cartesia#text-to-speech) | `cartesia` | Yes | Yes | No | -| [Deepgram](/providers/voice/deepgram#text-to-speech) | `deepgram` | Yes | Yes | Yes | -| [ElevenLabs](/providers/voice/elevenlabs#text-to-speech) | `11labs` | Yes | No | Yes | -| [Hume](/providers/voice/hume#text-to-speech) | `hume` | No | No | No | -| [Inworld](/providers/voice/inworld#text-to-speech) | `inworld` | No | No | No | -| [LMNT](/providers/voice/imnt#text-to-speech) | `lmnt` | No | No | No | -| [Microsoft](/providers/voice/microsoft#text-to-speech) | `microsoft` | No | No | No | -| [MiniMax](/providers/voice/minimax#text-to-speech) | `minimax` | No | No | No | -| [Neuphonic](/providers/voice/neuphonic#text-to-speech) | `neuphonic` | No | No | No | -| [OpenAI](/providers/voice/openai#text-to-speech) | `openai` | No | Yes | No | -| [PlayHT](/providers/voice/playht#text-to-speech) | `playht` | No | No | No | -| [Rime AI](/providers/voice/rimeai#text-to-speech) | `rime-ai` | Yes | No | No | -| [Sesame](/providers/voice/sesame#text-to-speech) | `sesame` | No | No | No | -| [Smallest AI](/providers/voice/smallest-ai#text-to-speech) | `smallest-ai` | No | No | No | -| [WellSaid](/providers/voice/wellsaid#text-to-speech) | `wellsaid` | Yes | No | Yes | -| [xAI](/providers/voice/xai#text-to-speech) | `xai` | Yes | Yes | No | +| Provider | Provider string | +| -- | -- | +| [Vapi Voices](/providers/voice/vapi-voices#text-to-speech) | `vapi` | +| [Azure](/providers/voice/azure#text-to-speech) | `azure` | +| [Cartesia](/providers/voice/cartesia#text-to-speech) | `cartesia` | +| [Deepgram](/providers/voice/deepgram#text-to-speech) | `deepgram` | +| [ElevenLabs](/providers/voice/elevenlabs#text-to-speech) | `11labs` | +| [Hume](/providers/voice/hume#text-to-speech) | `hume` | +| [Inworld](/providers/voice/inworld#text-to-speech) | `inworld` | +| [LMNT](/providers/voice/imnt#text-to-speech) | `lmnt` | +| [Microsoft](/providers/voice/microsoft#text-to-speech) | `microsoft` | +| [MiniMax](/providers/voice/minimax#text-to-speech) | `minimax` | +| [Neuphonic](/providers/voice/neuphonic#text-to-speech) | `neuphonic` | +| [OpenAI](/providers/voice/openai#text-to-speech) | `openai` | +| [PlayHT](/providers/voice/playht#text-to-speech) | `playht` | +| [Rime AI](/providers/voice/rimeai#text-to-speech) | `rime-ai` | +| [Sesame](/providers/voice/sesame#text-to-speech) | `sesame` | +| [Smallest AI](/providers/voice/smallest-ai#text-to-speech) | `smallest-ai` | +| [WellSaid](/providers/voice/wellsaid#text-to-speech) | `wellsaid` | +| [xAI](/providers/voice/xai#text-to-speech) | `xai` | ## Find a voice in the dashboard @@ -56,6 +56,8 @@ The **Voice Library** in the [Vapi Dashboard](https://dashboard.vapi.ai) lists e voice available to your organization. Browse and preview voices there, then copy a voice's ID to use on an assistant. +Language support can vary by model and voice. Test your selected voice with the language you plan to use before publishing your assistant. + In the [Vapi Dashboard](https://dashboard.vapi.ai), open **Resources**, then diff --git a/fern/providers/voice/rimeai.mdx b/fern/providers/voice/rimeai.mdx index 6c16d5e32..f86b176bc 100644 --- a/fern/providers/voice/rimeai.mdx +++ b/fern/providers/voice/rimeai.mdx @@ -5,99 +5,55 @@ description: Configure a Rime AI model and voice for a Vapi assistant and find i slug: providers/voice/rimeai --- -{/* Legacy marketing copy retained temporarily during provider-page standardization. - -**What is Rime.ai?** - -Rime.ai is a pioneering platform in the field of speech synthesis, offering real-time, lifelike voice generation. Specializing in creating natural-sounding voices tailored to demographic specifics, Rime.ai provides tools that allow businesses and developers to engage their audiences more effectively. By leveraging advanced AI, Rime.ai delivers high-quality audio that is indistinguishable from human speech, setting a new standard in the industry. - -**The Evolution of AI Speech Synthesis:** - -AI speech synthesis has come a long way from its early days of robotic-sounding outputs. Advances in machine learning, neural networks, and data processing have transformed synthetic speech into highly realistic and expressive audio. Rime.ai has harnessed these technological advancements to create voices that sound natural and convey the desired emotions and nuances. - -**Overview of Rime.ai’s Offerings:** - -Rime.ai provides a comprehensive suite of speech synthesis tools designed to meet various needs: - -**Real-time Speech Synthesis:** - -- Rime.ai’s real-time speech synthesis technology enables instant generation of lifelike voices. This is particularly useful for applications requiring immediate feedback, such as interactive voice response (IVR) systems, live virtual assistants, and real-time translation services. The technology boasts sub-300 millisecond response times, ensuring seamless and efficient communication. - -**Demographically Specific Voice Control:** - -- One of Rime.ai’s standout features is its ability to generate voices that are demographically specific. This means businesses can tailor their audio output to match the cultural, regional, and social characteristics of their target audience. With over 200 distinct voices available, Rime.ai allows for precise customization, enhancing user engagement and relatability. - -**Use Cases for Rime.ai:** - - -- Rime.ai’s technology is versatile and applicable across multiple sectors: - -**IVR Systems:** - -- Interactive voice response systems benefit greatly from Rime.ai’s real-time speech synthesis. By providing natural and clear voices, IVR systems can improve user interactions, reduce call handling times, and enhance overall customer satisfaction. - -**Newsreading:** - -In the media industry, Rime.ai’s lifelike voices can be used for automated newsreading, delivering news updates in a natural and engaging manner. This ensures consistency and professionalism in audio content delivery. - -**Narration:** - -- For audiobooks, educational materials, and other forms of narration, Rime.ai offers high-quality voice generation that enhances the listening experience. The ability to match voices to the content’s demographic audience further adds to the personalization and effectiveness of the narration. - -**Impact on Content Creation:** - -Rime.ai is revolutionizing content creation by providing tools that allow for quick and efficient production of high-quality audio. By eliminating the need for traditional recording methods, creators can save time and resources while still producing professional-grade content. This democratization of audio production opens up new opportunities for innovation and creativity. - -**Innovation and Research:** - -Rime.ai is committed to continuous innovation and research in speech synthesis technology. Their team of experts is dedicated to improving the naturalness, expressiveness, and versatility of AI-generated voices. By exploring new applications and refining existing technologies, Rime.ai aims to stay at the forefront of the industry. - -**AI Safety and Ethics:** - -Ensuring the ethical use of AI is a top priority for Rime.ai. They have implemented robust safeguards to prevent misuse of their technology and are actively involved in discussions about responsible AI development. Protecting user data and maintaining transparency in AI operations are central to their approach. - -**Integrations and Compatibility:** - -Rime.ai’s API allows seamless integration with various platforms and applications. This ensures that users can incorporate Rime.ai’s speech synthesis capabilities into their existing systems effortlessly, enhancing functionality and improving user experience. - -*/} - Rime AI provides streaming text-to-speech models and voices that you can use as a Vapi assistant's voice. You can use Rime AI through Vapi's default integration, or use your own Rime AI account by connecting it in [Integrations](/providers/integrations). ## Text-to-speech -Set `voice.provider` to `rime-ai`, `voice.model` to a Rime model (`arcana`, `mistv2`, or `mist`), and `voice.voiceId` to a voice. Rime AI offers many voices and supports voice cloning, you can browse and copy a voice's ID from the [Voice Library](/providers/voice/overview). +Set `voice.provider` to `rime-ai`, `voice.model` to a Rime model, and `voice.voiceId` to a voice. Rime AI offers many voices and supports voice cloning; browse and copy a voice's ID from the [Voice Library](/providers/voice/overview). ```bash curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \ -H "Authorization: Bearer $VAPI_API_KEY" \ -H "Content-Type: application/json" \ -d '{ - "voice": { "provider": "rime-ai", "model": "arcana", "voiceId": "VOICE_ID" } + "voice": { + "provider": "rime-ai", + "model": "arcana", + "voiceId": "luna", + "language": "en" + } }' ``` For additional API configuration options, review the [`RimeAIVoice` fields](/api-reference/assistants/create#request.body.voice.RimeAIVoice) in the Create Assistant API reference. -### Supported languages - -The following language values are currently accepted by Vapi for this provider. +### Supported models -| Language | Language code | +| Model | Model ID | | --- | --- | -| English | `en` | -| Spanish | `es` | -| German | `de` | -| French | `fr` | -| Arabic | `ar` | -| Hindi | `hi` | -| Japanese | `ja` | -| Hebrew | `he` | -| Portuguese | `pt` | -| Tamil | `ta` | -| Sinhala | `si` | +| Arcana | `arcana` | +| Mist v2 | `mistv2` | +| Mist | `mist` | + +### Supported languages + +Language support depends on the selected model. The following model and language combinations are currently supported by Vapi. + +| Language | Language code | Arcana | Mist v2 | Mist | +| --- | --- | --- | --- | --- | +| Arabic | `ar` | X | | | +| English | `en` | X | X | X | +| French | `fr` | X | X | X | +| German | `de` | X | X | X | +| Hebrew | `he` | X | | | +| Hindi | `hi` | X | | | +| Japanese | `ja` | X | | | +| Portuguese | `pt` | X | | | +| Sinhala | `si` | X | | | +| Spanish | `es` | X | X | X | +| Tamil | `ta` | X | | | ## Related diff --git a/fern/providers/voice/sesame.mdx b/fern/providers/voice/sesame.mdx index 730d745bc..ebe4502df 100644 --- a/fern/providers/voice/sesame.mdx +++ b/fern/providers/voice/sesame.mdx @@ -41,6 +41,10 @@ For additional API configuration options, review the [`SesameVoice` fields](/api | Savannah | `Savannah` | | Spencer | `Spencer` | +## Supported languages + +Sesame text-to-speech has no separate language setting. The `csm-1b` model is English. + ## Related diff --git a/fern/providers/voice/smallest-ai.mdx b/fern/providers/voice/smallest-ai.mdx index 28befd603..985053941 100644 --- a/fern/providers/voice/smallest-ai.mdx +++ b/fern/providers/voice/smallest-ai.mdx @@ -28,6 +28,10 @@ curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \ For additional API configuration options, review the [`SmallestAIVoice` fields](/api-reference/assistants/create#request.body.voice.SmallestAIVoice) in the Create Assistant API reference. +## Supported languages + +Smallest AI text-to-speech has no separate language setting. The Lightning model detects the language from the input text and supports multiple languages. + ## Related diff --git a/fern/providers/voice/wellsaid.mdx b/fern/providers/voice/wellsaid.mdx index 49afdf721..a57595cd1 100644 --- a/fern/providers/voice/wellsaid.mdx +++ b/fern/providers/voice/wellsaid.mdx @@ -28,6 +28,10 @@ curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \ For additional API configuration options, review the [`WellSaidVoice` fields](/api-reference/assistants/create#request.body.voice.WellSaidVoice) in the Create Assistant API reference. +## Supported languages + +WellSaid Labs text-to-speech has no separate language setting. Language is determined by the selected voice. Browse voices in the [Voice Library](/providers/voice/overview). + ## Related diff --git a/fern/providers/voice/xai.mdx b/fern/providers/voice/xai.mdx index 51f5cc3de..bf1a72f96 100644 --- a/fern/providers/voice/xai.mdx +++ b/fern/providers/voice/xai.mdx @@ -56,13 +56,13 @@ For additional API configuration options, review the [`XaiVoice` fields](/api-re | Language | Language code | | --- | --- | -| Automatic detection | `auto` | -| English | `en` | | Arabic (Egypt) | `ar-EG` | | Arabic (Saudi Arabia) | `ar-SA` | | Arabic (United Arab Emirates) | `ar-AE` | +| Automatic detection | `auto` | | Bengali | `bn` | | Chinese (Simplified) | `zh` | +| English | `en` | | French | `fr` | | German | `de` | | Hindi | `hi` | diff --git a/fern/security-and-privacy/hipaa.mdx b/fern/security-and-privacy/hipaa.mdx index 740b15729..c783bd97c 100644 --- a/fern/security-and-privacy/hipaa.mdx +++ b/fern/security-and-privacy/hipaa.mdx @@ -82,6 +82,7 @@ When enabling HIPAA compliance, only HIPAA compliant providers may be chosen. ### Transcription Providers (STT) - **Azure** +- **Cartesia** - **Deepgram** - **Soniox** - **xAI** diff --git a/fern/voice-fallback-plan.mdx b/fern/voice-fallback-plan.mdx index 1bab5ed10..b0ececd41 100644 --- a/fern/voice-fallback-plan.mdx +++ b/fern/voice-fallback-plan.mdx @@ -80,18 +80,11 @@ Add the `fallbackPlan` property to your assistant's voice configuration, and spe Each voice provider supports different configuration options. Expand the accordion below to see available settings for each provider. - - - **stability** (0-1): Controls voice consistency. Lower values allow more emotional range; higher values produce more stable output. - - **similarityBoost** (0-1): Enhances similarity to the original voice. Higher values make the voice more similar to the reference. - - **style** (0-1): Voice style intensity. Higher values amplify the speaker's style. - - **useSpeakerBoost** (boolean): Enable to boost similarity to the original speaker. - - **speed** (0.7-1.2): Speech speed multiplier. Default is 1.0. - - **optimizeStreamingLatency** (0-4): Controls streaming latency optimization. Default is 3. - - **enableSsmlParsing** (boolean): Enable SSML pronunciation support. - - **model**: Select from `eleven_multilingual_v2`, `eleven_turbo_v2`, `eleven_turbo_v2_5`, `eleven_flash_v2`, `eleven_flash_v2_5`, or `eleven_monolingual_v1`. + + - **speed** (0.5-2): Speech rate multiplier. Default is 1.0. - - **model**: Model selection (`sonic-english`, `sonic-3`, etc.). + - **model**: Select from `sonic-3.5`, `sonic-3.5-2026-05-04`, `sonic-3`, `sonic-3-2026-01-12`, or `sonic-3-2025-10-27`. - **language**: Language code for the voice. - **experimentalControls.speed**: Speech speed adjustment (-1 to 1). Negative values slow down; positive values speed up. - **experimentalControls.emotion**: Array of emotion configurations (e.g., `["happiness:high", "curiosity:medium"]`). @@ -100,65 +93,72 @@ Each voice provider supports different configuration options. Expand the accordi - **volume** (0.5-2.0): Volume adjustment. - **experimental.accentLocalization** (0 or 1): Toggle accent localization. - - - **speed** (0.5-2): Speech rate multiplier. Default is 1.0. - - - - **speed** (0.25-4): Speech speed multiplier. Default is 1.0. - - **model**: Select from `tts-1`, `tts-1-hd`, or realtime models. - - **instructions**: Voice prompt to control the generated audio style. Does not work with `tts-1` or `tts-1-hd` models. - - - - **speed** (0.25-2): Speech rate multiplier. Default is 1.0. - - **language**: Two-letter ISO 639-1 language code, or `auto` for auto-detection. - - - - **model**: Select from `arcana`, `mistv2`, or `mist`. Defaults to `arcana`. - - **speed** (0.1+): Speech speed multiplier. - - **pauseBetweenBrackets** (boolean): Enable pause control using angle brackets (e.g., `<200>` for 200ms pause). - - **phonemizeBetweenBrackets** (boolean): Enable phonemization using curly brackets (e.g., `{h'El.o}`). - - **reduceLatency** (boolean): Optimize for reduced streaming latency. - - **inlineSpeedAlpha**: Inline speed control using alpha notation. - - - - **speed** (0.1-5): Speech rate multiplier. - - **temperature** (0.1-2): Controls voice variance. Lower values are more predictable; higher values allow more variation. - - **emotion**: Emotion preset (e.g., `female_happy`, `male_sad`, `female_angry`, `male_surprised`). - - **voiceGuidance** (1-6): Controls voice uniqueness. Lower values reduce uniqueness. - - **styleGuidance** (1-30): Controls emotion intensity. Higher values create more emotional performance. - - **textGuidance** (1-2): Controls text adherence. Higher values are more accurate to input text. - - **model**: Select from `PlayHT2.0`, `PlayHT2.0-turbo`, `Play3.0-mini`, or `PlayDialog`. - - **model**: Select from `aura` or `aura-2`. Defaults to `aura-2`. - **mipOptOut** (boolean): Opt out of the Deepgram Model Improvement Partnership program. + + - **stability** (0-1): Controls voice consistency. Lower values allow more emotional range; higher values produce more stable output. + - **similarityBoost** (0-1): Enhances similarity to the original voice. Higher values make the voice more similar to the reference. + - **style** (0-1): Voice style intensity. Higher values amplify the speaker's style. + - **useSpeakerBoost** (boolean): Enable to boost similarity to the original speaker. + - **speed** (0.7-1.2): Speech speed multiplier. Default is 1.0. + - **optimizeStreamingLatency** (0-4): Controls streaming latency optimization. Default is 3. + - **enableSsmlParsing** (boolean): Enable SSML pronunciation support. + - **model**: Select from `eleven_flash_v2`, `eleven_flash_v2_5`, `eleven_multilingual_v2`, or `eleven_v3`. + - **model**: Model selection (e.g., `octave2`). - **description**: Natural language instructions describing how the speech should sound (tone, intonation, pacing, accent). - **isCustomHumeVoice** (boolean): Indicates whether using a custom Hume voice. + + - **speed** (0.25-2): Speech rate multiplier. Default is 1.0. + - **language**: Two-letter ISO 639-1 language code, or `auto` for auto-detection. + - - **model**: Select from `speech-02-hd` (high-fidelity) or `speech-02-turbo` (low latency). Defaults to `speech-02-turbo`. + - **model**: Select from `speech-02-hd`, `speech-02-turbo`, or `speech-2.5-turbo-preview`. Defaults to `speech-02-turbo`. - **emotion**: Emotion preset (`happy`, `sad`, `angry`, `fearful`, `surprised`, `disgusted`, `neutral`). - **pitch** (-12 to 12): Voice pitch adjustment in semitones. - **speed** (0.5-2): Speech speed adjustment. - **volume** (0.5-2): Volume adjustment. - - - **model**: Model selection. - - **enableSsml** (boolean): Enable limited SSML translation for input text. - - **libraryIds**: Array of library IDs to use for voice synthesis. - - **model**: Model selection (e.g., `neu_fast`). - **language**: Language code (required). - **speed** (0.25-2): Speech speed multiplier. + + - **speed** (0.25-4): Speech speed multiplier. Default is 1.0. + - **model**: Select from `tts-1`, `tts-1-hd`, or `gpt-4o-mini-tts`. + - **instructions**: Voice prompt to control the generated audio style. Does not work with `tts-1` or `tts-1-hd` models. + + + - **speed** (0.1-5): Speech rate multiplier. + - **temperature** (0.1-2): Controls voice variance. Lower values are more predictable; higher values allow more variation. + - **emotion**: Emotion preset (e.g., `female_happy`, `male_sad`, `female_angry`, `male_surprised`). + - **voiceGuidance** (1-6): Controls voice uniqueness. Lower values reduce uniqueness. + - **styleGuidance** (1-30): Controls emotion intensity. Higher values create more emotional performance. + - **textGuidance** (1-2): Controls text adherence. Higher values are more accurate to input text. + - **model**: Select from `PlayHT2.0`, `PlayHT2.0-turbo`, `Play3.0-mini`, or `PlayDialog`. + + + - **model**: Select from `arcana`, `mistv2`, or `mist`. Defaults to `arcana`. + - **speed** (0.1+): Speech speed multiplier. + - **pauseBetweenBrackets** (boolean): Enable pause control using angle brackets (e.g., `<200>` for 200ms pause). + - **phonemizeBetweenBrackets** (boolean): Enable phonemization using curly brackets (e.g., `{h'El.o}`). + - **reduceLatency** (boolean): Optimize for reduced streaming latency. + - **inlineSpeedAlpha**: Inline speed control using alpha notation. + - **model**: Model selection (e.g., `lightning`). - **speed**: Speech speed multiplier. + + - **model**: Model selection. + - **enableSsml** (boolean): Enable limited SSML translation for input text. + - **libraryIds**: Array of library IDs to use for voice synthesis. + ## Best practices