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

# Speech to Text

> Transcribe audio files to text using Whisper and Sarvam models.

## Request

```bash theme={null}
POST https://api.euron.one/api/v1/euri/audio/transcriptions
```

Send as **multipart/form-data**.

### Form parameters

<ParamField body="file" type="file" required>
  Audio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav, webm. Max size: 25 MB.
</ParamField>

<ParamField body="model" type="string">
  STT model ID. Options: `whisper-large-v3`, `whisper-large-v3-turbo`, `sarvam-stt`. Default: `whisper-large-v3-turbo`.
</ParamField>

<ParamField body="language" type="string">
  Language code (ISO 639-1). Example: `"en"`, `"hi"`, `"es"`.
</ParamField>

<ParamField body="response_format" type="string">
  Output format. Options: `"json"`, `"text"`, `"verbose_json"`. Default: `"json"`.
</ParamField>

<ParamField body="temperature" type="number">
  Sampling temperature for the model. Default: `0`.
</ParamField>

<ParamField body="prompt" type="string">
  Optional prompt to guide the transcription style.
</ParamField>

***

## Examples

<CodeGroup>
  ```bash cURL theme={null}
  curl -X POST https://api.euron.one/api/v1/euri/audio/transcriptions \
    -H "Authorization: Bearer YOUR_EURI_API_KEY" \
    -F "file=@recording.mp3" \
    -F "model=whisper-large-v3-turbo" \
    -F "language=en"
  ```

  ```python Python theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="YOUR_EURI_API_KEY",
      base_url="https://api.euron.one/api/v1/euri"
  )

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

  print(response.text)
  ```

  ```bash cURL (Sarvam Hindi) theme={null}
  curl -X POST https://api.euron.one/api/v1/euri/audio/transcriptions \
    -H "Authorization: Bearer YOUR_EURI_API_KEY" \
    -F "file=@hindi_audio.wav" \
    -F "model=sarvam-stt" \
    -F "language=hi"
  ```
</CodeGroup>

***

## Response

```json theme={null}
{
  "text": "Hello, welcome to the EURI API documentation."
}
```

## Pricing

| Model                    | Price per audio hour | Premium |
| ------------------------ | -------------------- | ------- |
| `whisper-large-v3`       | \$0.111              | Yes     |
| `whisper-large-v3-turbo` | \$0.04               | Yes     |
| `sarvam-stt`             | \$0.33               | Yes     |

<Note>All STT models are premium and require wallet balance.</Note>