Mistral AI Audio API

openapi: 3.1.0
info:
  title: Mistral AI Agents Audio API
  description: Agent completions API for building AI agents that can handle complex tasks, maintain context, coordinate multiple actions, and use tools including function calling. Agents are created and configured via the Mistral platform and invoked through this API.
  version: '1.0'
  contact:
    name: Mistral AI Support
    url: https://docs.mistral.ai/
    email: support@mistral.ai
  termsOfService: https://mistral.ai/terms/
servers:
- url: https://api.mistral.ai/v1
  description: Mistral AI Production
security:
- bearerAuth: []
tags:
- name: Audio
  description: Audio transcription operations
paths:
  /audio/transcriptions:
    post:
      operationId: createTranscription
      summary: Mistral AI Create an audio transcription
      description: Transcribe audio to text using Voxtral. Supports multiple audio formats, speaker diarization, word-level timestamps, context biasing with custom vocabulary, and 13 languages.
      tags:
      - Audio
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/TranscriptionRequest'
      responses:
        '200':
          description: Transcription result
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TranscriptionResponse'
        '400':
          description: Bad request
        '401':
          description: Unauthorized
        '429':
          description: Rate limit exceeded
components:
  schemas:
    TranscriptionResponse:
      type: object
      properties:
        text:
          type: string
          description: The full transcribed text
        language:
          type: string
          description: Detected or specified language code
        duration:
          type: number
          description: Duration of the audio in seconds
        words:
          type: array
          items:
            $ref: '#/components/schemas/Word'
          description: Word-level details when verbose_json format is used
        segments:
          type: array
          items:
            $ref: '#/components/schemas/Segment'
          description: Segment-level details when verbose_json format is used
    Word:
      type: object
      properties:
        word:
          type: string
          description: The transcribed word
        start:
          type: number
          description: Start time in seconds
        end:
          type: number
          description: End time in seconds
        speaker:
          type:
          - integer
          - 'null'
          description: Speaker ID if diarization is enabled
    Segment:
      type: object
      properties:
        id:
          type: integer
          description: Segment index
        start:
          type: number
          description: Start time in seconds
        end:
          type: number
          description: End time in seconds
        text:
          type: string
          description: Transcribed text for this segment
        speaker:
          type:
          - integer
          - 'null'
          description: Speaker ID if diarization is enabled
    TranscriptionRequest:
      type: object
      required:
      - model
      - file
      properties:
        model:
          type: string
          description: The transcription model to use
          examples:
          - mistral-audio-latest
        file:
          type: string
          format: binary
          description: The audio file to transcribe (WAV, MP3, FLAC, OGG, M4A, WEBM)
        language:
          type: string
          description: ISO 639-1 language code. If not specified, the language is auto-detected.
          examples:
          - en
          - fr
          - de
          - es
        prompt:
          type: string
          description: Context or vocabulary hints to improve transcription accuracy. Useful for domain-specific terminology.
        response_format:
          type: string
          enum:
          - json
          - text
          - verbose_json
          default: json
          description: Output format for the transcription
        temperature:
          type: number
          minimum: 0
          maximum: 1
          default: 0
          description: Sampling temperature for transcription
        timestamp_granularities:
          type: array
          items:
            type: string
            enum:
            - word
            - segment
          description: Granularity levels for timestamps
        diarization:
          type: boolean
          default: false
          description: Whether to enable speaker diarization
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: Mistral AI API key passed as a Bearer token
externalDocs:
  description: Mistral AI Agents API Documentation
  url: https://docs.mistral.ai/api/endpoint/agents