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

# Audio & Transcription

> Transcribe spoken audio to text using Whisper-1 and Whisper Large models.

The `/v1/audio/transcriptions` endpoint provides full OpenAI Audio API parity for multilingual speech-to-text processing.

<CodeGroup>
  ```python Python (OpenAI SDK) icon="python" theme={"theme":{"light":"ayu-dark","dark":"catppuccin-latte"}}
  from openai import OpenAI
  import os

  client = OpenAI(
      base_url="https://api.neosantara.xyz/v1",
      api_key=os.environ["NEOSANTARA_API_KEY"]
  )

  with open("recording.mp3", "rb") as audio_file:
      transcription = client.audio.transcriptions.create(
          model="whisper-large-v3-turbo",
          file=audio_file,
          language="en",
          response_format="json"
      )

  print(transcription.text)
  ```

  ```bash cURL icon="terminal" theme={"theme":{"light":"ayu-dark","dark":"catppuccin-latte"}}
  curl -X POST https://api.neosantara.xyz/v1/audio/transcriptions \
    -H "Authorization: Bearer $NEOSANTARA_API_KEY" \
    -F file="@recording.mp3" \
    -F model="whisper-large-v3-turbo" \
    -F language="en"
  ```
</CodeGroup>

## Transcription Parameters

| Parameter         | Type     | Required | Description                                               |
| :---------------- | :------- | :------- | :-------------------------------------------------------- |
| `file`            | `binary` | Yes      | Audio file payload sent as multipart/form-data.           |
| `model`           | `string` | Yes      | `whisper-large-v3-turbo` or `whisper-1`.                  |
| `language`        | `string` | Optional | ISO-639-1 language code (e.g., `id`, `en`).               |
| `prompt`          | `string` | Optional | Contextual vocabulary or domain glossary hint.            |
| `response_format` | `string` | Optional | Output representation: `json`, `text`, or `verbose_json`. |
| `temperature`     | `number` | Optional | Sampling temperature between `0` and `1`. Default `0`.    |

## Supported Formats

* Audio containers: `mp3`, `mp4`, `m4a`, `wav`, `webm`, `ogg`, `flac`.
* Standard upload ceiling: 25 MB per request.


## Related topics

- [Chat Completions](/en/gateway/chat-completions.md)
- [Model Catalog](/en/gateway/models.md)
- [File Management](/en/gateway/operations/files.md)