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

# Create a translation

> Transcribe audio and translate it to English

Send `multipart/form-data`.

| Field             | Type   | Required | Description                                                       |
| ----------------- | ------ | -------- | ----------------------------------------------------------------- |
| `file`            | file   | Yes      | Audio to translate.                                               |
| `model`           | string | Yes      | Audio model supporting translation.                               |
| `prompt`          | string | No       | Style guidance or context.                                        |
| `response_format` | string | No       | json, text, srt, verbose\_json, or vtt, subject to model support. |
| `temperature`     | number | No       | Sampling temperature.                                             |

<CodeGroup>
  ```bash cURL theme={null}
  curl https://api.bianxie.ai/v1/audio/translations \
    -H "Authorization: Bearer API_KEY" \
    -F "model=your-model" \
    -F "file=@speech.mp3"
  ```

  ```python Python theme={null}
  client.audio.translations.create(model="your-model", file=open("speech.mp3", "rb"))
  ```

  ```javascript Node.js theme={null}
  await client.audio.translations.create({ model: "your-model", file: fs.createReadStream("speech.mp3") });
  ```
</CodeGroup>

The response contains English `text`; verbose formats may also include segments and timestamps. Treat this endpoint as non-streaming by default.