> ## Documentation Index
> Fetch the complete documentation index at: https://docs.budecosystem.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Translate Audio

> Convert audio files to English text regardless of input language.

<RequestExample>
  ```bash cURL theme={null}
  curl https://gateway.bud.studio/v1/audio/translations \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -F "file=@french_audio.mp3" \
    -F "model=whisper-1" \
    -F "response_format=json"
  ```
</RequestExample>

<ResponseExample>
  ```json 200 theme={null}
  {
    "text": "Hello, this is the translated English text."
  }
  ```
</ResponseExample>

## Headers

| Parameter     | Type   | Required | Description                   |
| ------------- | ------ | -------- | ----------------------------- |
| Authorization | string | Yes      | Bearer authentication header  |
| Content-Type  | string | Yes      | Must be `multipart/form-data` |

## Form Data

| Parameter        | Type   | Required | Description                                                                                                              |
| ---------------- | ------ | -------- | ------------------------------------------------------------------------------------------------------------------------ |
| file             | file   | Yes      | Audio file to translate (max 25MB). Supported formats: `flac`, `mp3`, `mp4`, `mpeg`, `mpga`, `m4a`, `ogg`, `wav`, `webm` |
| model            | string | Yes      | Model identifier (e.g., `whisper-1`)                                                                                     |
| prompt           | string | No       | Optional text to guide the model's style or continue previous audio segment                                              |
| response\_format | string | No       | Format of the transcript output: `json`, `text`, `srt`, `verbose_json`, `vtt`. Default: `json`                           |
| temperature      | float  | No       | Sampling temperature (0.0 to 1.0). Default: 0.0                                                                          |

## Supported Providers

<CardGroup cols={3}>
  <Card title="OpenAI" icon="openai">
    Whisper models that translate any language to English
  </Card>

  <Card title="Azure OpenAI" icon="microsoft">
    Enterprise-grade audio translation with Whisper models
  </Card>

  <Card title="Fireworks" icon="fire">
    Fast Whisper v3 models for efficient audio translation
  </Card>
</CardGroup>