TranscriptionRequest

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/TranscriptionRequest",
  "title": "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"
    }
  }
}