Deepgram Audio API

openapi: 3.2.0
info:
  title: REST Audio API
  version: 1.0.0
servers:
- url: https://agent.deepgram.com
  description: Production
- url: https://api.deepgram.com
  description: Base
tags:
- name: Audio
paths:
  /v1/speak:
    post:
      operationId: audio_generate
      summary: Text to Speech transformation
      description: Convert text into natural-sounding speech using Deepgram's TTS REST API
      tags:
      - Audio
      parameters:
      - name: callback
        in: query
        description: URL to which we'll make the callback request
        required: false
        schema:
          type: string
      - name: callback_method
        in: query
        description: HTTP method by which the callback request will be made
        required: false
        schema:
          $ref: '#/components/schemas/V1SpeakPostParametersCallbackMethod'
          default: POST
      - name: mip_opt_out
        in: query
        description: Opts out requests from the Deepgram Model Improvement Program. Refer to our Docs for pricing impacts before setting this to true. https://dpgr.am/deepgram-mip
        required: false
        schema:
          type: boolean
          default: false
      - name: tag
        in: query
        description: Label your requests for the purpose of identification during usage reporting
        required: false
        schema:
          $ref: '#/components/schemas/V1SpeakPostParametersTag'
      - name: bit_rate
        in: query
        description: The bitrate of the audio in bits per second. Choose from predefined ranges or specific values based on the encoding type.
        required: false
        schema:
          $ref: '#/components/schemas/V1SpeakPostParametersBitRate'
          default: 48000
      - name: container
        in: query
        description: Container specifies the file format wrapper for the output audio. The available options depend on the encoding type.
        required: false
        schema:
          $ref: '#/components/schemas/V1SpeakPostParametersContainer'
          default: wav
      - name: encoding
        in: query
        description: Encoding allows you to specify the expected encoding of your audio output
        required: false
        schema:
          $ref: '#/components/schemas/V1SpeakPostParametersEncoding'
          default: mp3
      - name: model
        in: query
        description: AI model used to process submitted text
        required: false
        schema:
          $ref: '#/components/schemas/V1SpeakPostParametersModel'
          default: aura-asteria-en
      - name: sample_rate
        in: query
        description: Sample Rate specifies the sample rate for the output audio. Based on the encoding, different sample rates are supported. For some encodings, the sample rate is not configurable
        required: false
        schema:
          $ref: '#/components/schemas/V1SpeakPostParametersSampleRate'
          default: 24000
      - name: speed
        in: query
        description: Speaking rate multiplier that adjusts the pace of generated speech while preserving natural prosody and voice quality. Not yet supported in all languages.
        required: false
        schema:
          type: number
          format: double
          minimum: 0.7
          maximum: 1.5
          default: 1
      responses:
        '200':
          description: Successful text-to-speech transformation
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/speak_v1_audio_generate_Response_200'
        '400':
          description: Invalid Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      requestBody:
        description: Transform text to speech
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SpeakV1Request'
      security:
      - ApiKeyAuth: []
  /v2/speak:
    post:
      operationId: audio_generate_2
      summary: Flux Text to Speech (batch)
      description: Synthesize a complete block of text into a single audio response using Deepgram's Flux TTS batch (REST) API. Use this for pre-rendering fixed audio (IVR prompts, notifications, narration) where the whole text is known up front and you don't need incremental playback or interruption.
      tags:
      - Audio
      parameters:
      - name: callback
        in: query
        description: URL to which we'll make the callback request
        required: false
        schema:
          type: string
      - name: callback_method
        in: query
        description: HTTP method by which the callback request will be made
        required: false
        schema:
          $ref: '#/components/schemas/V2SpeakPostParametersCallbackMethod'
          default: POST
      - name: mip_opt_out
        in: query
        description: Opts out requests from the Deepgram Model Improvement Program. Refer to our Docs for pricing impacts before setting this to true. https://dpgr.am/deepgram-mip
        required: false
        schema:
          type: boolean
          default: false
      - name: tag
        in: query
        description: Label your requests for the purpose of identification during usage reporting
        required: false
        schema:
          $ref: '#/components/schemas/V2SpeakPostParametersTag'
      - name: bit_rate
        in: query
        description: The bitrate of the audio in bits per second. Choose from predefined ranges or specific values based on the encoding type.
        required: false
        schema:
          $ref: '#/components/schemas/V2SpeakPostParametersBitRate'
          default: 48000
      - name: container
        in: query
        description: Container specifies the file format wrapper for the output audio. The available options depend on the encoding type.
        required: false
        schema:
          $ref: '#/components/schemas/V2SpeakPostParametersContainer'
          default: wav
      - name: encoding
        in: query
        description: Encoding allows you to specify the expected encoding of your audio output
        required: false
        schema:
          $ref: '#/components/schemas/V2SpeakPostParametersEncoding'
          default: mp3
      - name: expressivity
        in: query
        description: 'Expressive range of the generated speech, on a calm-to-animated axis. Accepted values: `-2`, `-1`, `0`, `1`, `2`. `0` (the default) is the voice''s tuned delivery and the production-validated setting, with `-2` the calm end of the range and `2` the animated end. Supported on all Flux voices; applies to the whole request. Beta: behavior may change in future model versions, and non-default values increase the risk of hallucinations and pronunciation errors; audition before shipping. An invalid value is rejected with a `400` — `EXPRESSIVITY_OUT_OF_RANGE` for a value outside the range, `EXPRESSIVITY_INCREMENT_INVALID` for a fractional value. See [Expressivity](/docs/tts-expressivity).'
        required: false
        schema:
          $ref: '#/components/schemas/V2SpeakPostParametersExpressivity'
          default: 0
      - name: model
        in: query
        description: Flux TTS model used to synthesize the submitted text, in the form `flux-{voice}-{language}` (for example, `flux-alexis-en`). Required; unlike the v1 (Aura) endpoint there is no default and only flux models are accepted. English-only at launch.
        required: true
        schema:
          type: string
      - name: sample_rate
        in: query
        description: Sample Rate specifies the sample rate for the output audio. Based on the encoding, different sample rates are supported. For some encodings, the sample rate is not configurable
        required: false
        schema:
          $ref: '#/components/schemas/V2SpeakPostParametersSampleRate'
          default: 24000
      - name: speed
        in: query
        description: Speaking rate multiplier that adjusts the pace of generated speech while preserving natural prosody and voice quality. Accepted values run `0.5` to `1.5` in `0.05` increments. Not yet supported in all languages. When the text contains an inline pause marker, speed is capped at `1.15` (`PAUSE_SPEED_CAP_EXCEEDED` above that). A value other than `1.0` cannot be combined with inline pronunciation controls (`CONTROL_COMBINATION_INVALID`).
        required: false
        schema:
          type: number
          format: double
          minimum: 0.5
          maximum: 1.5
          multipleOf: 0.05
          default: 1
      - name: priority
        in: query
        description: Processing priority for asynchronous (callback) requests. The only supported value is low.
        required: false
        schema:
          $ref: '#/components/schemas/V2SpeakPostParametersPriority'
      responses:
        '200':
          description: 'Returns the synthesized audio in the requested encoding as a binary stream. When a `callback` URL is supplied, the request is processed asynchronously and the response body is instead a JSON acknowledgement (Content-Type `application/json`) of the form {"request_id": "..."}, with the audio delivered to the callback URL. Because this endpoint is typed as a binary audio stream, SDK callers that set `callback` receive this JSON acknowledgement through the audio byte iterator as raw bytes and must join the chunks and parse `request_id` themselves.'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/SpeakV2AcceptedResponse'
        '400':
          description: 'Invalid Request. Inline control violations return a structured error whose `err_code` names the rule: `CONTROL_COMBINATION_INVALID` (pronunciation combined with speed or pause, or all three together), `PAUSE_SPEED_CAP_EXCEEDED` (a pause marker with `speed` above `1.15`), `BREAK_OUT_OF_RANGE` (a pause outside 500-3000 ms), `BREAK_INCREMENT_INVALID` (a pause off the 100 ms grid), `BREAKS_LIMIT_EXCEEDED` (more than 8 pause markers, or two pauses with no text between them), `BREAK_SYNTAX_INVALID` (a malformed pause marker, such as a simple marker without backslashes or an escaped structured marker), plus the existing pronunciation and speed codes. A `speed` of `1.0` does not count as a speed control for the combination rules. See [Speed, Pause, Pronunciation](/docs/tts-voice-controls).'
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      requestBody:
        description: Transform text to speech
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SpeakV2Request'
      security:
      - ApiKeyAuth: []
components:
  schemas:
    V1SpeakPostParametersEncoding0:
      type: string
      enum:
      - linear16
      description: Encoding - linear16. Uncompressed, high-quality audio format often used for telephony or audio processing.
      title: V1SpeakPostParametersEncoding0
    V2SpeakPostParametersEncoding5:
      type: string
      enum:
      - opus
      description: Encoding - opus. High-compression audio format optimized for real-time communications.
      title: V2SpeakPostParametersEncoding5
    V2SpeakPostParametersSampleRate2:
      type: string
      enum:
      - '8000'
      - '16000'
      description: Encoding - alaw. Supported sample rates - 8000, 16000 Hz.
      title: V2SpeakPostParametersSampleRate2
    V1SpeakPostParametersSampleRate2:
      type: string
      enum:
      - '8000'
      - '16000'
      description: Encoding - alaw. Supported sample rates - 8000, 16000 Hz.
      title: V1SpeakPostParametersSampleRate2
    V2SpeakPostParametersBitRate0:
      type: string
      enum:
      - '8000'
      - '16000'
      - '24000'
      - '32000'
      - '40000'
      - '48000'
      description: Encoding - mp3(default). Supported bitrates - 8000, 16000, 24000, 32000, 40000, 48000(default) bps.
      title: V2SpeakPostParametersBitRate0
    SpeakV2AcceptedResponse:
      type: object
      properties:
        request_id:
          type: string
          format: uuid
          description: Unique identifier for tracking the asynchronous request
      required:
      - request_id
      description: Accepted response returned when a callback URL is supplied; the audio is delivered asynchronously to that URL.
      title: SpeakV2AcceptedResponse
    V2SpeakPostParametersBitRate:
      oneOf:
      - $ref: '#/components/schemas/V2SpeakPostParametersBitRate0'
      - type: integer
        minimum: 4000
        maximum: 650000
      - type: integer
        minimum: 4000
        maximum: 192000
      title: V2SpeakPostParametersBitRate
    V1SpeakPostParametersSampleRate4:
      type: string
      enum:
      - '48000'
      description: Encoding - opus. Sample rate is fixed at 48000 Hz.
      title: V1SpeakPostParametersSampleRate4
    V2SpeakPostParametersContainer1:
      type: string
      enum:
      - wav
      description: Encoding - linear16. Supported container - wav (default), or no container.
      title: V2SpeakPostParametersContainer1
    V1SpeakPostParametersEncoding:
      oneOf:
      - $ref: '#/components/schemas/V1SpeakPostParametersEncoding0'
      - $ref: '#/components/schemas/V1SpeakPostParametersEncoding1'
      - $ref: '#/components/schemas/V1SpeakPostParametersEncoding2'
      - $ref: '#/components/schemas/V1SpeakPostParametersEncoding3'
      - $ref: '#/components/schemas/V1SpeakPostParametersEncoding4'
      - $ref: '#/components/schemas/V1SpeakPostParametersEncoding5'
      - $ref: '#/components/schemas/V1SpeakPostParametersEncoding6'
      title: V1SpeakPostParametersEncoding
    V2SpeakPostParametersExpressivity:
      type: string
      enum:
      - '-2'
      - '-1'
      - '0'
      - '1'
      - '2'
      title: V2SpeakPostParametersExpressivity
    V1SpeakPostParametersEncoding2:
      type: string
      enum:
      - mulaw
      description: Encoding - mulaw. Compressed audio format commonly used in telephony.
      title: V1SpeakPostParametersEncoding2
    V2SpeakPostParametersContainer3:
      type: string
      enum:
      - wav
      description: Encoding - alaw. Supported container - wav (default), or no container.
      title: V2SpeakPostParametersContainer3
    V2SpeakPostParametersSampleRate:
      oneOf:
      - $ref: '#/components/schemas/V2SpeakPostParametersSampleRate0'
      - $ref: '#/components/schemas/V2SpeakPostParametersSampleRate1'
      - $ref: '#/components/schemas/V2SpeakPostParametersSampleRate2'
      - $ref: '#/components/schemas/V2SpeakPostParametersSampleRate3'
      title: V2SpeakPostParametersSampleRate
    V1SpeakPostParametersSampleRate1:
      type: string
      enum:
      - '8000'
      - '16000'
      description: Encoding - mulaw. Supported sample rates - 8000, 16000 Hz.
      title: V1SpeakPostParametersSampleRate1
    V1SpeakPostParametersContainer1:
      type: string
      enum:
      - wav
      description: Encoding - linear16. Supported container - wav (default), or no container.
      title: V1SpeakPostParametersContainer1
    V1SpeakPostParametersBitRate:
      oneOf:
      - $ref: '#/components/schemas/V1SpeakPostParametersBitRate0'
      - type: number
        format: double
        minimum: 4000
        maximum: 650000
      - type: number
        format: double
        minimum: 4000
        maximum: 192000
      title: V1SpeakPostParametersBitRate
    speak_v1_audio_generate_Response_200:
      type: object
      properties: {}
      description: Empty response body
      title: speak_v1_audio_generate_Response_200
    V2SpeakPostParametersEncoding6:
      type: string
      enum:
      - aac
      description: Encoding - aac. Advanced audio format offering better quality at smaller file sizes than mp3.
      title: V2SpeakPostParametersEncoding6
    V1SpeakPostParametersSampleRate3:
      type: string
      enum:
      - '22050'
      description: Encoding - mp3. Sample rate is fixed and not configurable (22050 Hz).
      title: V1SpeakPostParametersSampleRate3
    V2SpeakPostParametersContainer:
      oneOf:
      - $ref: '#/components/schemas/V2SpeakPostParametersContainer0'
      - $ref: '#/components/schemas/V2SpeakPostParametersContainer1'
      - $ref: '#/components/schemas/V2SpeakPostParametersContainer2'
      - $ref: '#/components/schemas/V2SpeakPostParametersContainer3'
      - $ref: '#/components/schemas/V2SpeakPostParametersContainer4'
      title: V2SpeakPostParametersContainer
    V2SpeakPostParametersContainer4:
      type: string
      enum:
      - ogg
      description: Encoding - opus. Supported container - ogg (default).
      title: V2SpeakPostParametersContainer4
    ErrorResponseLegacyError:
      type: object
      properties:
        err_code:
          type: string
          description: The error code
        err_msg:
          type: string
          description: The error message
        request_id:
          type: string
          description: The request ID
      title: ErrorResponseLegacyError
    V2SpeakPostParametersCallbackMethod:
      type: string
      enum:
      - POST
      - PUT
      default: POST
      title: V2SpeakPostParametersCallbackMethod
    ErrorResponseTextError:
      type: string
      title: ErrorResponseTextError
    V2SpeakPostParametersSampleRate3:
      type: string
      enum:
      - '8000'
      - '16000'
      - '22050'
      - '32000'
      - '48000'
      description: Encoding - flac. Supported sample rates - 8000, 16000, 22050, 32000, 48000 Hz.
      title: V2SpeakPostParametersSampleRate3
    V1SpeakPostParametersContainer4:
      type: string
      enum:
      - ogg
      description: Encoding - opus. Supported container - ogg (default).
      title: V1SpeakPostParametersContainer4
    ErrorResponse:
      oneOf:
      - $ref: '#/components/schemas/ErrorResponseTextError'
      - $ref: '#/components/schemas/ErrorResponseLegacyError'
      - $ref: '#/components/schemas/ErrorResponseModernError'
      title: ErrorResponse
    V2SpeakPostParametersEncoding2:
      type: string
      enum:
      - mulaw
      description: Encoding - mulaw. Compressed audio format commonly used in telephony.
      title: V2SpeakPostParametersEncoding2
    V1SpeakPostParametersBitRate0:
      type: string
      enum:
      - '32000'
      - '48000'
      description: Encoding - mp3(default). Supported bitrates - 32000, 48000(default) bps.
      title: V1SpeakPostParametersBitRate0
    V1SpeakPostParametersEncoding4:
      type: string
      enum:
      - mp3
      description: Encoding - mp3. Popular compressed audio format for music and streaming.
      title: V1SpeakPostParametersEncoding4
    V1SpeakPostParametersEncoding5:
      type: string
      enum:
      - opus
      description: Encoding - opus. High-compression audio format optimized for real-time communications.
      title: V1SpeakPostParametersEncoding5
    V1SpeakPostParametersContainer3:
      type: string
      enum:
      - wav
      description: Encoding - alaw. Supported container - wav (default), or no container.
      title: V1SpeakPostParametersContainer3
    SpeakV2Request:
      type: object
      properties:
        text:
          type: string
          description: 'The text content to be converted to speech. The server normalizes and preprocesses the text before synthesis. May contain inline pause controls (`\{pause:500ms\}`, 500-3000 ms in 100 ms steps, at most 8 per request) and inline pronunciation controls (`\{"word": "...", "pronounce": "<IPA>"\}`, Early Access). Pronunciation cannot be combined with pause or with a `speed` other than `1.0`, and `speed` is capped at `1.15` when a pause is present. See [Speed, Pause, Pronunciation](/docs/tts-voice-controls).'
      required:
      - text
      description: Request body for Flux TTS batch (REST) text-to-speech conversion. The full block of text is synthesized in a single request and returned as one audio response.
      title: SpeakV2Request
    V1SpeakPostParametersCallbackMethod:
      type: string
      enum:
      - POST
      - PUT
      default: POST
      title: V1SpeakPostParametersCallbackMethod
    V1SpeakPostParametersContainer2:
      type: string
      enum:
      - wav
      description: Encoding - mulaw. Supported container - wav (default), or no container.
      title: V1SpeakPostParametersContainer2
    V2SpeakPostParametersEncoding3:
      type: string
      enum:
      - alaw
      description: Encoding - alaw. Similar to mulaw but used in international telephony.
      title: V2SpeakPostParametersEncoding3
    SpeakV1Request:
      type: object
      properties:
        text:
          type: string
          description: The text content to be converted to speech
      required:
      - text
      description: Request body for text-to-speech conversion
      title: SpeakV1Request
    ErrorResponseModernError:
      type: object
      properties:
        category:
          type: string
          description: The category of the error
        message:
          type: string
          description: A message about the error
        details:
          type: string
          description: A description of the error
        request_id:
          type: string
          description: The unique identifier of the request
      title: ErrorResponseModernError
    V1SpeakPostParametersEncoding1:
      type: string
      enum:
      - flac
      description: Encoding - flac. Lossless audio format for high-quality compression.
      title: V1SpeakPostParametersEncoding1
    V2SpeakPostParametersTag:
      oneOf:
      - type: string
      - type: array
        items:
          type: string
      title: V2SpeakPostParametersTag
    V1SpeakPostParametersSampleRate:
      oneOf:
      - $ref: '#/components/schemas/V1SpeakPostParametersSampleRate0'
      - $ref: '#/components/schemas/V1SpeakPostParametersSampleRate1'
      - $ref: '#/components/schemas/V1SpeakPostParametersSampleRate2'
      - $ref: '#/components/schemas/V1SpeakPostParametersSampleRate3'
      - $ref: '#/components/schemas/V1SpeakPostParametersSampleRate4'
      title: V1SpeakPostParametersSampleRate
    V1SpeakPostParametersEncoding6:
      type: string
      enum:
      - aac
      description: Encoding - aac. Advanced audio format offering better quality at smaller file sizes than mp3.
      title: V1SpeakPostParametersEncoding6
    V1SpeakPostParametersModel:
      type: string
      enum:
      - aura-angus-en
      - aura-arcas-en
      - aura-asteria-en
      - aura-athena-en
      - aura-helios-en
      - aura-hera-en
      - aura-luna-en
      - aura-orion-en
      - aura-orpheus-en
      - aura-perseus-en
      - aura-stella-en
      - aura-zeus-en
      - aura-2-amalthea-en
      - aura-2-andromeda-en
      - aura-2-apollo-en
      - aura-2-arcas-en
      - aura-2-aries-en
      - aura-2-asteria-en
      - aura-2-athena-en
      - aura-2-atlas-en
      - aura-2-aurora-en
      - aura-2-callista-en
      - aura-2-cora-en
      - aura-2-cordelia-en
      - aura-2-delia-en
      - aura-2-draco-en
      - aura-2-electra-en
      - aura-2-harmonia-en
      - aura-2-helena-en
      - aura-2-hera-en
      - aura-2-hermes-en
      - aura-2-hyperion-en
      - aura-2-iris-en
      - aura-2-janus-en
      - aura-2-juno-en
      - aura-2-jupiter-en
      - aura-2-luna-en
      - aura-2-mars-en
      - aura-2-minerva-en
      - aura-2-neptune-en
      - aura-2-odysseus-en
      - aura-2-ophelia-en
      - aura-2-orion-en
      - aura-2-orpheus-en
      - aura-2-pandora-en
      - aura-2-phoebe-en
      - aura-2-pluto-en
      - aura-2-saturn-en
      - aura-2-selene-en
      - aura-2-thalia-en
      - aura-2-theia-en
      - aura-2-vesta-en
      - aura-2-zeus-en
      - aura-2-agustina-es
      - aura-2-alvaro-es
      - aura-2-antonia-es
      - aura-2-aquila-es
      - aura-2-carina-es
      - aura-2-celeste-es
      - aura-2-diana-es
      - aura-2-estrella-es
      - aura-2-gloria-es
      - aura-2-javier-es
      - aura-2-luciano-es
      - aura-2-nestor-es
      - aura-2-olivia-es
      - aura-2-selena-es
      - aura-2-silvia-es
      - aura-2-sirio-es
      - aura-2-valerio-es
      - aura-2-aurelia-de
      - aura-2-elara-de
      - aura-2-fabian-de
      - aura-2-julius-de
      - aura-2-kara-de
      - aura-2-lara-de
      - aura-2-viktoria-de
      - aura-2-beatrix-nl
      - aura-2-cornelia-nl
      - aura-2-daphne-nl
      - aura-2-hestia-nl
      - aura-2-lars-nl
      - aura-2-leda-nl
      - aura-2-rhea-nl
      - aura-2-roman-nl
      - aura-2-sander-nl
      - aura-2-agathe-fr
      - aura-2-hector-fr
      - aura-2-cesare-it
      - aura-2-cinzia-it
      - aura-2-demetra-it
      - aura-2-dionisio-it
      - aura-2-elio-it
      - aura-2-flavio-it
      - aura-2-livia-it
      - aura-2-maia-it
      - aura-2-melia-it
      - aura-2-ama-ja
      - aura-2-ebisu-ja
      - aura-2-fujin-ja
      - aura-2-izanami-ja
      - aura-2-uzume-ja
      default: aura-asteria-en
      title: V1SpeakPostParametersModel
    V2SpeakPostParametersEncoding:
      oneOf:
      - $ref: '#/components/schemas/V2SpeakPostParametersEncoding0'
      - $ref: '#/components/schemas/V2SpeakPostParametersEncoding1'
      - $ref: '#/components/schemas/V2SpeakPostParametersEncoding2'
      - $ref: '#/components/schemas/V2SpeakPostParametersEncoding3'
      - $ref: '#/components/schemas/V2SpeakPostParametersEncoding4'
      - $ref: '#/components/schemas/V2SpeakPostParametersEncoding5'
      - $ref: '#/components/schemas/V2SpeakPostParametersEncoding6'
      title: V2SpeakPostParametersEncoding
    V2SpeakPostParametersSampleRate0:
      type: string
      enum:
      - '8000'
      - '16000'
      - '24000'
      - '32000'
      - '44100'
      - '48000'
      description: Encoding - linear16. Supported sample rates - 8000, 16000, 24000, 32000, 44100, 48000 Hz.
      title: V2SpeakPostParametersSampleRate0
    V1SpeakPostParametersEncoding3:
      type: string
      enum:
      - alaw
      description: Encoding - alaw. Similar to mulaw but used in international telephony.
      title: V1SpeakPostParametersEncoding3
    V2SpeakPostParametersEncoding4:
      type: string
      enum:
      - mp3
      description: Encoding - mp3. Popular compressed audio format for music and streaming.
      title: V2SpeakPostParametersEncoding4
    V2SpeakPostParametersEncoding1:
      type: string
      enum:
      - flac
      description: Encoding - flac. Lossless audio format for high-quality compression.
      title: V2SpeakPostParametersEncoding1
    V1SpeakPostParametersContainer0:
      type: string
      enum:
      - none
      description: No container.
      title: V1SpeakPostParametersContainer0
    V1SpeakPostParametersContainer:
      oneOf:
      - $ref: '#/components/schemas/V1SpeakPostParametersContainer0'
      - $ref: '#/components/schemas/V1SpeakPostParametersContainer1'
      - $ref: '#/components/schemas/V1SpeakPostParametersContainer2'
      - $ref: '#/components/schemas/V1SpeakPostParametersContainer3'
      - $ref: '#/components/schemas/V1SpeakPostParametersContainer4'
      title: V1SpeakPostParametersContainer
    V2SpeakPostParametersPriority:
      type: string
      enum:
      - low
      title: V2SpeakPostParametersPriority
    V2SpeakPostParametersEncoding0:
      type: string
      enum:
      - linear16
      description: Encoding - linear16. Uncompressed, high-quality audio format often used for telephony or audio processing.
      title: V2SpeakPostParametersEncoding0
    V2SpeakPostParametersContainer0:
      type: string
      enum:
      - none
      description: No container.
      title: V2SpeakPostParametersContainer0
    V2SpeakPostParametersContainer2:
      type: string
      enum:
      - wav
      description: Encoding - mulaw. Supported container - wav (default), or no container.
      title: V2SpeakPostParametersContainer2
    V2SpeakPostParametersSampleRate1:
      type: string
      enum:
      - '8000'
      - '16000'
      description: Encoding - mulaw. Supported sample rates - 8000, 16000 Hz.
      title: V2SpeakPostParametersSampleRate1
    V1SpeakPostParametersTag:
      oneOf:
      - type: string
      - type: array
        items:
          type: string
      title: V1SpeakPostParametersTag
    V1SpeakPostParametersSampleRate0:
      type: string
      enum:
      - '8000'
      - '16000'
      - '24000'
      - '32000'
      - '48000'
      description: Encoding - linear16. Supported sample rates - 8000, 16000, 24000, 32000, 48000 Hz.
      title: V1SpeakPostParametersSampleRate0
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: Authorization
      description: 'Use `Authorization: Token <API_KEY>`

        Example: `Authorization: Token 12345abcdef`

        '
    JwtAuth:
      type: http
      scheme: bearer
      description: 'Use `Authorization: Bearer <JWT>`

        Example: `Authorization: Bearer eyJhbGciOiJ...`

        '