MiniMax Text to Audio API

openapi: 3.1.0
info:
  title: MiniMax Files Text to Audio API
  description: MiniMax text generation API with support for chat completion and streaming output
  license:
    name: MIT
  version: 1.0.0
servers:
- url: https://api.minimax.io
security:
- bearerAuth: []
tags:
- name: Text to Audio
paths:
  /v1/t2a_v2:
    post:
      summary: Text to Audio V2
      description: Convert text to audio using MiniMax T2A V2 API with support for streaming and non-streaming output
      operationId: t2aV2
      tags:
      - Text to Audio
      requestBody:
        description: T2A V2 request parameters
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/T2aV2Req'
        required: true
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/T2aV2Resp'
        '400':
          description: Bad request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Authentication failed
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
  /v1/t2a_async_v2:
    post:
      summary: Text to Audio Async V2
      description: Convert text to audio asynchronously using MiniMax T2A Async V2 API with support for long text processing
      operationId: t2aAsyncV2
      tags:
      - Text to Audio
      requestBody:
        description: T2A Async V2 request parameters
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/T2AAsyncV2Req'
        required: true
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/T2AAsyncV2Resp'
        '400':
          description: Bad request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Authentication failed
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
  /v1/query/t2a_async_query_v2:
    post:
      summary: Query T2A Async V2 Task Status
      description: Query the status of an asynchronous text-to-audio task
      operationId: t2aAsyncV2Query
      tags:
      - Text to Audio
      requestBody:
        description: Query request parameters
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/T2AAsyncV2QueryReq'
        required: true
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/T2AAsyncV2QueryResp'
        '400':
          description: Bad request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '401':
          description: Authentication failed
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
components:
  schemas:
    T2AAsyncV2QueryReq:
      type: object
      required:
      - task_id
      - group_id
      properties:
        task_id:
          type: integer
          format: int64
          description: Task ID to query
        group_id:
          type: string
          description: Group ID
    PronunciationDict:
      type: object
      properties:
        tone:
          type: array
          description: Tone replacement list
          items:
            type: string
        phonetic:
          type: array
          description: Phonetic correction list
          items:
            type: string
    T2AStreamOption:
      type: object
      properties:
        include_usage:
          type: boolean
          description: Whether to include usage information
    VoiceModify:
      type: object
      properties:
        modify_type:
          type: string
          description: Voice modification type
        modify_value:
          type: number
          format: double
          description: Modification value
    T2AAsyncV2Req:
      type: object
      required:
      - model
      - voice_setting
      properties:
        model:
          type: string
          description: Model ID for text-to-audio conversion
          enum:
          - speech-2.5-hd-preview
          - speech-2.5-turbo-preview
          - speech-02-hd
          - speech-02-turbo
          - speech-01-hd
          - speech-01-turbo
        text:
          type: string
          description: Text content to convert to audio
        text_file_id:
          type: integer
          format: int64
          description: Text file ID for file-based input
        voice_setting:
          $ref: '#/components/schemas/T2AAsyncV2VoiceSetting'
        audio_setting:
          $ref: '#/components/schemas/T2AAsyncV2AudioSetting'
        pronunciation_dict:
          $ref: '#/components/schemas/T2AAsyncV2PronunciationDict'
        language_boost:
          type: string
          description: Language boost setting
        callback_url:
          type: string
          description: Callback URL for task completion notification
        voice_modify:
          $ref: '#/components/schemas/VoiceModify'
        aigc_watermark:
          type: boolean
          description: Whether to add AIGC watermark
    T2aV2Resp:
      type: object
      properties:
        data:
          $ref: '#/components/schemas/StreamData'
        extra_info:
          $ref: '#/components/schemas/T2AExtraInfo'
        trace_id:
          type: string
          description: Trace ID for request tracking
    T2aV2Req:
      type: object
      required:
      - model
      - text
      properties:
        model:
          type: string
          description: Model ID for text-to-audio conversion
          enum:
          - speech-2.5-hd-preview
          - speech-2.5-turbo-preview
          - speech-02-hd
          - speech-02-turbo
          - speech-01-hd
          - speech-01-turbo
        text:
          type: string
          description: Text content to convert to audio
        voice_setting:
          $ref: '#/components/schemas/T2AVoiceSetting'
        audio_setting:
          $ref: '#/components/schemas/T2AAudioSetting'
        pronunciation_dict:
          $ref: '#/components/schemas/PronunciationDict'
        timber_weights:
          type: array
          description: Timbre weights (legacy field)
          items:
            $ref: '#/components/schemas/TimbreWeights'
        speed_rate:
          type: integer
          format: int64
          description: Speed rate for audio generation
        stream:
          type: boolean
          description: Whether to enable streaming output
        language_boost:
          type: string
          description: Language boost setting
        subtitle_enable:
          type: boolean
          description: Whether to enable subtitle generation
        output_format:
          type: string
          description: Output audio format
        voice_modify:
          $ref: '#/components/schemas/VoiceModify'
        stream_options:
          $ref: '#/components/schemas/T2AStreamOption'
        subtitle_type:
          type: string
          description: Subtitle type
        aigc_watermark:
          type: boolean
          description: Whether to add AIGC watermark
        with_propagator_meta:
          type: boolean
          description: Whether to add propagator metadata
        timbre_weights:
          type: array
          description: Timbre weights (takes priority over timber_weights)
          items:
            $ref: '#/components/schemas/TimbreWeights'
    T2AAsyncV2AudioSetting:
      type: object
      properties:
        audio_sample_rate:
          type: integer
          format: int64
          description: Audio sample rate
        bitrate:
          type: integer
          format: int64
          description: Bitrate
        format:
          type: string
          description: Generated audio file format
        channel:
          $ref: '#/components/schemas/Channel'
        force_cbr:
          type: boolean
          description: Force CBR encoding
    T2AAsyncV2Resp:
      type: object
      properties:
        task_id:
          type: integer
          format: int64
          description: Task ID for tracking the async operation
        task_token:
          type: string
          description: Task token for authentication
        file_id:
          type: integer
          format: int64
          description: Expected file ID for downloading the result
        usage_characters:
          type: integer
          format: int64
          description: Estimated character consumption
    TimbreWeights:
      type: object
      properties:
        weight:
          type: number
          format: double
          description: Weight value
        voice_id:
          type: string
          description: Voice ID
    T2AExtraInfo:
      type: object
      properties:
        usage:
          $ref: '#/components/schemas/T2AUsage'
    Error:
      type: object
      required:
      - error
      - message
      properties:
        error:
          type: integer
          format: int32
          description: Error code
        message:
          type: string
          description: Error message
    T2AAudioSetting:
      type: object
      properties:
        sample_rate:
          type: integer
          format: int64
          description: Sample rate
        bitrate:
          type: integer
          format: int64
          description: Bitrate
        format:
          type: string
          description: Audio format
        channel:
          type: integer
          format: int64
          description: Number of audio channels
        force_cbr:
          type: boolean
          description: Force CBR (only effective for MP3 format)
    T2AVoiceSetting:
      type: object
      required:
      - voice_id
      properties:
        speed:
          type: number
          format: double
          description: Speech speed
        vol:
          type: number
          format: double
          description: Volume level
        pitch:
          type: integer
          format: int64
          description: Pitch level
        voice_id:
          type: string
          description: Voice ID
        emotion:
          type: string
          description: Emotion setting
        latex_read:
          type: boolean
          description: Whether to read LaTeX
        add_silence:
          type: number
          format: double
          description: Add silence between sentences
        english_normalization:
          type: boolean
          description: Whether to normalize English text
        text_normalization:
          type: boolean
          description: Whether to normalize text
    T2AAsyncV2QueryResp:
      type: object
      properties:
        status:
          type: string
          description: Task status
          enum:
          - success
          - failed
          - expired
          - processing
        task_id:
          type: integer
          format: int64
          description: Task ID
        file_id:
          type: integer
          format: int64
          description: File ID for downloading the result
    T2AAsyncV2VoiceSetting:
      type: object
      required:
      - voice_id
      properties:
        voice_id:
          type: string
          description: Voice ID
        speed:
          type: number
          format: double
          description: 'Speech speed (default: 1.0)'
        vol:
          type: number
          format: double
          description: 'Volume level (default: 1.0)'
        pitch:
          type: integer
          format: int64
          description: 'Pitch level (default: 0)'
        emotion:
          type: string
          description: Emotion setting
        english_normalization:
          type: boolean
          description: Whether to normalize English text (legacy field)
        add_silence:
          type: number
          format: double
          description: Add silence between sentences
        text_normalization:
          type: boolean
          description: Whether to normalize text
    StreamData:
      type: object
      properties:
        audio:
          type: string
          description: Generated audio segment in base64 encoding
        status:
          type: integer
          format: int64
          description: 'Current audio stream status (1: generating, 2: completed)'
        ced:
          type: string
          description: Generation progress in bytes
        subtitle_file:
          type: string
          description: Subtitle file
        subtitle:
          $ref: '#/components/schemas/T2ASubtitle'
    Channel:
      type: string
      enum:
      - Mono
      - Binaural
      description: Audio channel configuration
    T2ASubtitle:
      type: object
      properties:
        text:
          type: string
          description: Subtitle text
        start_time:
          type: number
          format: double
          description: Start time in seconds
        end_time:
          type: number
          format: double
          description: End time in seconds
    T2AUsage:
      type: object
      properties:
        total_characters:
          type: integer
          format: int64
          description: Total characters processed
        total_tokens:
          type: integer
          format: int64
          description: Total tokens used
    T2AAsyncV2PronunciationDict:
      type: object
      properties:
        tone:
          type: array
          description: Tone specification list for specific phrases
          items:
            type: string
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT