# Transcribe audio

`POST /v1/audio/transcriptions`

Converts audio into text

## Authorizations

Bearer authentication — send `Authorization: Bearer <token>`.

## Request Body (multipart/form-data) — required

```json
{
  "type": "object",
  "properties": {
    "file": {
      "type": "string",
      "format": "binary",
      "description": "Audio file",
      "example": ""
    },
    "model": {
      "type": "string",
      "example": "whisper-1"
    },
    "language": {
      "type": "string",
      "description": "ISO-639-1 language code",
      "example": ""
    },
    "prompt": {
      "type": "string",
      "example": ""
    },
    "response_format": {
      "type": "string",
      "enum": [
        "json",
        "text",
        "srt",
        "verbose_json",
        "vtt"
      ],
      "default": "json",
      "example": "json"
    },
    "temperature": {
      "type": "number",
      "example": ""
    },
    "timestamp_granularities": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "word",
          "segment"
        ]
      },
      "example": ""
    }
  },
  "required": [
    "file",
    "model"
  ]
}
```

## Responses

### 200 — Transcription returned

```json
{
  "type": "object",
  "properties": {
    "text": {
      "type": "string"
    }
  }
}
```