Telnyx Text To Speech Commands API

openapi: 3.2.0
info:
  contact:
    email: support@telnyx.com
  description: Telnyx provides global communications and connectivity APIs for developers — including SIP trunking, programmable voice, SMS, MMS, WhatsApp Business Messaging, Call Control, Fax, Wireless (IoT & eSIM), Phone Numbers (DID provisioning & porting), Emergency Services, and Network APIs for private interconnects and edge connectivity. Build, scale, and manage voice, messaging, and data networks with Telnyx's carrier-grade global infrastructure and API-first platform.
  title: Telnyx Text To Speech Commands API
  version: 2.0.0
  x-endpoint-cost: light
servers:
- description: Version 2.0.0 of the Telnyx API
  url: https://api.telnyx.com/v2
security:
- bearerAuth: []
tags:
- description: Text to speech streaming command operations
  name: Text To Speech Commands
paths:
  /text-to-speech/speech:
    get:
      description: 'Open a WebSocket connection to stream text and receive synthesized audio in real time. Authentication is provided via the standard `Authorization: Bearer <API_KEY>` header. Send JSON frames with text to synthesize; receive JSON frames containing base64-encoded audio chunks.


        Supported providers: `aws`, `telnyx`, `azure`, `murfai`, `minimax`, `rime`, `resemble`, `elevenlabs`, `xai`.


        **Connection flow:**

        1. Open WebSocket with query parameters specifying provider, voice, and model.

        2. Send an initial handshake message `{"text": " "}` (single space) with optional `voice_settings` to initialize the session.

        3. Send text messages as `{"text": "Hello world"}`.

        4. Receive audio chunks as JSON frames with base64-encoded audio.

        5. A final frame with `isFinal: true` indicates the end of audio for the current text.


        To interrupt and restart synthesis mid-stream, send `{"force": true}` — the current worker is stopped and a new one is started.


        **Note:** The Telnyx `Ultra` model is not available over WebSocket. Use the HTTP POST `/text-to-speech/speech` endpoint instead.'
      operationId: TextToSpeechOverWs
      parameters:
      - $ref: '#/components/parameters/voice'
      - $ref: '#/components/parameters/provider'
      - $ref: '#/components/parameters/model_id'
      - $ref: '#/components/parameters/voice_id'
      - $ref: '#/components/parameters/disable_cache'
      - $ref: '#/components/parameters/audio_format'
      - $ref: '#/components/parameters/socket_id'
      responses:
        '101':
          content:
            application/json:
              schema:
                oneOf:
                - $ref: '#/components/schemas/ClientTextFrame'
                - $ref: '#/components/schemas/TtsServerEvent'
          description: 'WebSocket connection established. Communication proceeds via JSON frames.


            **Client → Server:** See `ClientTextFrame` schema.

            **Server → Client:** See `AudioChunkFrame`, `FinalFrame`, and `ErrorFrame` schemas.'
        '200':
          description: WebSocket upgrade successful — this response is not returned directly. See 101 for frame documentation.
        '400':
          description: Invalid parameters — provider not supported or missing required fields.
        '401':
          description: Authentication failed — missing or invalid `x-telnyx-auth-rev2` header.
      summary: Stream text to speech over WebSocket
      tags:
      - Text To Speech Commands
      x-latency-category: interactive
    post:
      description: 'Generate synthesized speech audio from text input. Returns audio in the requested format (binary audio stream, base64-encoded JSON, or an audio URL for later retrieval).


        Authentication is provided via the standard `Authorization: Bearer <API_KEY>` header.


        The `voice` parameter provides a convenient shorthand to specify provider, model, and voice in a single string (e.g. `telnyx.NaturalHD.Alloy` or `Telnyx.Ultra.<voice_id>`). Alternatively, specify `provider` explicitly along with provider-specific parameters.


        Supported providers: `aws`, `telnyx`, `azure`, `elevenlabs`, `minimax`, `rime`, `resemble`, `xai`.


        The Telnyx `Ultra` model supports 44 languages with emotion control, speed adjustment, and volume control. Use the `telnyx` provider-specific parameters to configure these features.'
      operationId: generateSpeech
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/GenerateSpeechRequest'
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Base64AudioResponse'
            audio/mpeg:
              schema:
                description: Raw audio bytes. Returned when `output_type` is `binary_output` (default).
                format: binary
                type: string
          description: 'Speech generated successfully. The response format depends on the `output_type` parameter:

            - `binary_output` (default): Returns raw audio bytes with the appropriate `Content-Type` header (e.g. `audio/mpeg`).

            - `base64_output`: Returns a JSON object with `base64_audio` field.'
        '400':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/text-to-speech_ErrorResponse'
          description: Bad request — invalid parameters or provider error.
        '401':
          description: Authentication failed — missing or invalid API key.
        '422':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ValidationErrorResponse'
          description: Validation failed — invalid or missing required fields.
      summary: Generate speech from text
      tags:
      - Text To Speech Commands
      x-latency-category: interactive
  /text-to-speech/voices:
    get:
      description: 'Retrieve a list of available voices from one or all TTS providers. When `provider` is specified, returns voices for that provider only. Otherwise, returns voices from all providers.


        Some providers (ElevenLabs, Resemble) require an API key to list voices.'
      operationId: listVoices
      parameters:
      - description: Filter voices by provider. If omitted, voices from all providers are returned.
        in: query
        name: provider
        required: false
        schema:
          enum:
          - aws
          - telnyx
          - azure
          - elevenlabs
          - minimax
          - rime
          - resemble
          - xai
          type: string
      - description: API key for providers that require one to list voices (e.g. ElevenLabs).
        in: query
        name: api_key
        required: false
        schema:
          type: string
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VoicesResponse'
          description: List of available voices.
        '400':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/text-to-speech_ErrorResponse'
          description: Bad request — invalid provider or missing required API key.
        '401':
          description: Authentication failed — missing or invalid API key.
      summary: List available voices
      tags:
      - Text To Speech Commands
      x-latency-category: interactive
components:
  parameters:
    model_id:
      description: 'Model identifier for the chosen provider. Examples: `Natural`, `NaturalHD`, `Ultra` (Telnyx); `Polly.Generative` (AWS).'
      in: query
      name: model_id
      required: false
      schema:
        type: string
    voice_id:
      description: Voice identifier for the chosen provider.
      in: query
      name: voice_id
      required: false
      schema:
        type: string
    audio_format:
      description: Audio output format override. Supported for Telnyx models. `pcm` and `wav` are available for `Natural`/`NaturalHD` models. The `Ultra` model outputs PCM at 24kHz s16le or MP3 at 128kbps 24kHz.
      in: query
      name: audio_format
      required: false
      schema:
        enum:
        - pcm
        - wav
        - mp3
        type: string
    socket_id:
      description: Client-provided socket identifier for tracking. If not provided, one is generated server-side.
      in: query
      name: socket_id
      required: false
      schema:
        type: string
    disable_cache:
      description: When `true`, bypass the audio cache and generate fresh audio.
      in: query
      name: disable_cache
      required: false
      schema:
        default: false
        type: boolean
    provider:
      description: TTS provider. Defaults to `telnyx` if not specified. Ignored when `voice` is provided.
      in: query
      name: provider
      required: false
      schema:
        default: telnyx
        enum:
        - aws
        - telnyx
        - azure
        - elevenlabs
        - minimax
        - murfai
        - rime
        - resemble
        - xai
        type: string
    voice:
      description: Voice identifier in the format `provider.model_id.voice_id` or `provider.voice_id` (e.g. `telnyx.NaturalHD.Telnyx_Alloy`, `Telnyx.Ultra.<voice_id>`, or `azure.en-US-AvaMultilingualNeural`). When provided, the `provider`, `model_id`, and `voice_id` are extracted automatically. Takes precedence over individual `provider`/`model_id`/`voice_id` parameters.
      in: query
      name: voice
      required: false
      schema:
        type: string
  schemas:
    ErrorFrame:
      description: Server-to-client frame indicating an error during synthesis. The connection is closed shortly after.
      properties:
        error:
          description: Error message describing what went wrong.
          type: string
        type:
          const: error
          description: Frame type identifier.
          type: string
      type: object
    GenerateSpeechRequest:
      description: Request body for generating speech from text.
      properties:
        aws:
          $ref: '#/components/schemas/AwsProviderParams'
        azure:
          $ref: '#/components/schemas/AzureProviderParams'
        disable_cache:
          default: false
          description: When `true`, bypass the audio cache and generate fresh audio.
          type: boolean
        elevenlabs:
          $ref: '#/components/schemas/ElevenLabsProviderParams'
        language:
          description: Language code (e.g. `en-US`). Usage varies by provider.
          type: string
        minimax:
          $ref: '#/components/schemas/MinimaxProviderParams'
        output_type:
          default: binary_output
          description: Determines the response format. `binary_output` returns raw audio bytes, `base64_output` returns base64-encoded audio in JSON.
          enum:
          - binary_output
          - base64_output
          type: string
        provider:
          description: TTS provider. Required unless `voice` is provided.
          enum:
          - aws
          - telnyx
          - azure
          - elevenlabs
          - minimax
          - rime
          - resemble
          - xai
          type: string
        resemble:
          $ref: '#/components/schemas/ResembleProviderParams'
        rime:
          $ref: '#/components/schemas/RimeProviderParams'
        telnyx:
          $ref: '#/components/schemas/TelnyxProviderParams'
        text:
          description: The text to convert to speech.
          type: string
        text_type:
          description: Text type. Use `ssml` for SSML-formatted input (supported by AWS and Azure).
          enum:
          - text
          - ssml
          type: string
        voice:
          description: 'Voice identifier in the format `provider.model_id.voice_id` or `provider.voice_id`. Examples: `telnyx.NaturalHD.Alloy`, `Telnyx.Ultra.<voice_id>`, `azure.en-US-AvaMultilingualNeural`, `aws.Polly.Generative.Lucia`. When provided, `provider`, `model_id`, and `voice_id` are extracted automatically and take precedence over individual parameters.'
          type: string
        voice_settings:
          additionalProperties: true
          description: Provider-specific voice settings. Contents vary by provider — see provider-specific parameter objects below.
          type: object
        xai:
          $ref: '#/components/schemas/XAIProviderParams'
      type: object
    ClientTextFrame:
      description: Client-to-server frame containing text to synthesize.
      examples:
      - text: ' '
        voice_settings:
          voice_speed: 1.2
      - text: Hello, welcome to Telnyx text to speech.
      - force: true
        text: New text after interruption.
      properties:
        force:
          description: When `true`, stops the current synthesis worker and starts a new one. Used to interrupt speech mid-stream and begin synthesizing new text.
          type: boolean
        text:
          description: Text to convert to speech. Send `" "` (single space) as an initial handshake with optional `voice_settings`. Subsequent messages contain the actual text to synthesize.
          type: string
        voice_settings:
          additionalProperties: true
          description: 'Provider-specific voice settings sent with the initial handshake. Contents vary by provider — e.g. `{"speed": 1.2}` for Minimax, `{"voice_speed": 1.5}` for Telnyx.'
          type: object
      required:
      - text
      type: object
    VoicesResponse:
      description: List of available voices.
      properties:
        voices:
          items:
            $ref: '#/components/schemas/Voice'
          type: array
      type: object
    AwsProviderParams:
      description: AWS Polly provider-specific parameters.
      properties:
        language_code:
          description: Language code (e.g. `en-US`, `es-ES`).
          type: string
        lexicon_names:
          description: List of lexicon names to apply.
          items:
            type: string
          type: array
        output_format:
          description: Audio output format.
          type: string
        sample_rate:
          description: Audio sample rate.
          type: string
        text_type:
          description: Input text type.
          enum:
          - text
          - ssml
          type: string
      type: object
    TtsServerEvent:
      description: Union of all server-to-client WebSocket events for TTS streaming.
      discriminator:
        mapping:
          audio_chunk: '#/components/schemas/AudioChunkFrame'
          error: '#/components/schemas/ErrorFrame'
          final: '#/components/schemas/FinalFrame'
        propertyName: type
      oneOf:
      - $ref: '#/components/schemas/AudioChunkFrame'
      - $ref: '#/components/schemas/FinalFrame'
      - $ref: '#/components/schemas/ErrorFrame'
    ValidationErrorResponse:
      properties:
        errors:
          additionalProperties:
            items:
              type: string
            type: array
          description: Validation error details keyed by field name.
          type: object
      type: object
    RimeProviderParams:
      description: Rime provider-specific parameters.
      properties:
        response_format:
          description: Audio output format.
          type: string
        sampling_rate:
          description: Audio sampling rate in Hz.
          type: integer
        voice_speed:
          description: Voice speed multiplier.
          format: float
          type: number
      type: object
    ElevenLabsProviderParams:
      description: ElevenLabs provider-specific parameters.
      properties:
        api_key:
          description: Custom ElevenLabs API key. If not provided, the default Telnyx key is used.
          type: string
        language_code:
          description: Language code.
          type: string
        voice_settings:
          additionalProperties: true
          description: ElevenLabs voice settings (stability, similarity_boost, etc.).
          type: object
      type: object
    text-to-speech_ErrorResponse:
      properties:
        errors:
          items:
            properties:
              code:
                description: Error code.
                type: string
              detail:
                description: Detailed error description.
                type: string
              title:
                description: Error title.
                type: string
            type: object
          type: array
      type: object
    MinimaxProviderParams:
      description: Minimax provider-specific parameters.
      properties:
        language_boost:
          description: Language code to boost pronunciation for.
          type: string
        pitch:
          description: Pitch adjustment.
          type: integer
        response_format:
          description: Audio output format.
          type: string
        speed:
          description: Speech speed multiplier.
          format: float
          type: number
        vol:
          description: Volume level.
          format: float
          type: number
      type: object
    FinalFrame:
      description: Server-to-client frame indicating synthesis is complete for the current text.
      properties:
        audio:
          description: Always `null` for the final frame.
          type: 'null'
        isFinal:
          const: true
          description: Always `true`.
          type: boolean
        text:
          description: Empty string.
          type: string
        timeToFirstAudioFrameMs:
          description: Present if this was the first response frame.
          type: integer
        type:
          const: final
          description: Frame type identifier.
          type: string
      type: object
    Voice:
      description: A voice available for text-to-speech synthesis.
      properties:
        gender:
          description: Voice gender.
          type: string
        language:
          description: Language code.
          type: string
        name:
          description: Voice name.
          type: string
        provider:
          description: The TTS provider.
          type: string
        voice_id:
          description: Voice identifier.
          type: string
      type: object
    ResembleProviderParams:
      description: Resemble AI provider-specific parameters.
      properties:
        api_key:
          description: Custom Resemble API key.
          type: string
        format:
          description: Audio output format.
          type: string
        precision:
          description: Synthesis precision.
          type: string
        sample_rate:
          description: Audio sample rate.
          type: string
      type: object
    AudioChunkFrame:
      description: Server-to-client frame containing a base64-encoded audio chunk.
      properties:
        audio:
          description: Base64-encoded audio data. May be `null` for providers that use `drop_concatenated_audio` mode (Telnyx Natural/NaturalHD, Rime, Minimax, MurfAI, Resemble) — in that case only streamed chunks carry audio.
          type:
          - string
          - 'null'
        cached:
          description: Whether this audio was served from cache.
          type: boolean
        isFinal:
          description: Always `false` for audio chunk frames.
          type: boolean
        text:
          description: The text segment that this audio chunk corresponds to.
          type:
          - string
          - 'null'
        timeToFirstAudioFrameMs:
          description: Milliseconds from the start-of-speech request to the first audio frame. Only present on the first audio chunk of a synthesis request.
          type: integer
        type:
          const: audio_chunk
          description: Frame type identifier.
          type: string
      type: object
    Base64AudioResponse:
      description: Response when `output_type` is `base64_output`.
      properties:
        base64_audio:
          description: Base64-encoded audio data.
          type: string
      type: object
    AzureProviderParams:
      description: Azure Cognitive Services provider-specific parameters.
      properties:
        api_key:
          description: Custom Azure API key. If not provided, the default Telnyx key is used.
          type: string
        deployment_id:
          description: Custom Azure deployment ID.
          type: string
        effect:
          description: Azure audio effect to apply.
          type: string
        gender:
          description: Voice gender preference.
          type: string
        language_code:
          default: en-US
          description: Language code (e.g. `en-US`).
          type: string
        output_format:
          default: audio-24khz-160kbitrate-mono-mp3
          description: Azure audio output format.
          type: string
        region:
          description: Azure region (e.g. `eastus`, `westeurope`).
          type: string
        text_type:
          default: text
          description: Input text type. Use `ssml` for SSML-formatted input.
          enum:
          - text
          - ssml
          type: string
      type: object
    TelnyxProviderParams:
      description: Telnyx provider-specific parameters. Use `voice_speed` and `temperature` for `Natural` and `NaturalHD` models. For the `Ultra` model, use `voice_speed`, `volume`, and `emotion`.
      properties:
        emotion:
          description: Emotion control for the Ultra model. Adjusts the emotional tone of the synthesized speech.
          enum:
          - neutral
          - happy
          - sad
          - angry
          - fearful
          - disgusted
          - surprised
          type: string
        response_format:
          default: mp3
          description: Audio response format.
          type: string
        sampling_rate:
          default: 24000
          description: Audio sampling rate in Hz.
          type: integer
        temperature:
          default: 0.5
          description: Sampling temperature. Applies to `Natural` and `NaturalHD` models only.
          format: float
          type: number
        voice_speed:
          default: 1.0
          description: 'Voice speed multiplier. Applies to all models. Range: 0.5 to 2.0.'
          format: float
          maximum: 2.0
          minimum: 0.5
          type: number
        volume:
          default: 1.0
          description: 'Volume level for the Ultra model. Range: 0.0 to 2.0.'
          format: float
          maximum: 2.0
          minimum: 0.0
          type: number
      type: object
    XAIProviderParams:
      description: xAI provider-specific parameters.
      properties:
        language:
          default: auto
          description: Language code, or `auto` to detect.
          type: string
        output_format:
          default: mp3
          description: Audio output format.
          enum:
          - mp3
          - wav
          - pcm
          - mulaw
          - alaw
          type: string
        sample_rate:
          default: 24000
          description: Audio sample rate in Hz.
          enum:
          - 8000
          - 16000
          - 22050
          - 24000
          - 44100
          - 48000
          type: integer
        voice_id:
          description: xAI voice identifier.
          enum:
          - eve
          - ara
          - rex
          - sal
          - leo
          type: string
      required:
      - voice_id
      type: object
  securitySchemes:
    bearerAuth:
      scheme: bearer
      type: http
    branded-calling_bearerAuth:
      description: API key passed as a Bearer token in the Authorization header
      scheme: bearer
      type: http
    oauthClientAuth:
      description: OAuth 2.0 authentication for Telnyx API and MCP integrations
      flows:
        authorizationCode:
          authorizationUrl: https://api.telnyx.com/v2/oauth/authorize
          refreshUrl: https://api.telnyx.com/v2/oauth/token
          scopes:
            admin: Administrative access to Telnyx resources
          tokenUrl: https://api.telnyx.com/v2/oauth/token
        clientCredentials:
          scopes:
            admin: Administrative access to Telnyx resources
          tokenUrl: https://api.telnyx.com/v2/oauth/token
      type: oauth2
    outbound-voice-profiles_bearerAuth:
      bearerFormat: JWT
      scheme: bearer
      type: http
    pronunciation-dicts_bearerAuth:
      description: Telnyx API v2 key. Obtain from https://portal.telnyx.com
      scheme: bearer
      type: http
    stored-payment-transactions_bearerAuth:
      bearerFormat: JWT
      scheme: bearer
      type: http