CreateTranscriptionRequest

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/CreateTranscriptionRequest",
  "title": "CreateTranscriptionRequest",
  "type": "object",
  "required": [
    "file",
    "model"
  ],
  "properties": {
    "file": {
      "type": "string",
      "format": "binary",
      "description": "The audio file to transcribe (flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm)"
    },
    "model": {
      "type": "string",
      "description": "The model to use for transcription (whisper-1)",
      "examples": [
        "whisper-1"
      ]
    },
    "language": {
      "type": "string",
      "description": "The language of the input audio in ISO-639-1 format"
    },
    "prompt": {
      "type": "string",
      "description": "Optional text to guide the model's style or continue a previous segment"
    },
    "response_format": {
      "type": "string",
      "enum": [
        "json",
        "text",
        "srt",
        "verbose_json",
        "vtt"
      ],
      "default": "json",
      "description": "The format of the transcription output"
    },
    "temperature": {
      "type": "number",
      "minimum": 0,
      "maximum": 1,
      "default": 0,
      "description": "Sampling temperature between 0 and 1"
    },
    "timestamp_granularities": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "word",
          "segment"
        ]
      },
      "description": "The timestamp granularities to populate"
    }
  }
}