---
title: Speech to text
---

# Speech to text
POST *https://api.turing.sh/audio/stt*

## Parameters


- **model**
  - Type: string
  - Required: false
  - Description: Model to use for speech to text
  - Options: whisper, fast-whisper, gladia
  - Default: fast-whisper

- **audio**
  - Type: string
  - Required: true
  - Description: Audio URL to transcribe

- **diarization**
  - Type: boolean
  - Required: false
  - Description: Whether to use diarization or not

- **type**
  - Type: string
  - Required: false
  - Options: tiny, base, small, medium, large-v1, large-v2
  - Default: base

- **stream**
  - Type: boolean
  - Required: false

## Response

<Error>Response not defined yet</Error>


## Examples

<CodeGroup title="Speech to text example">
  ```typescript
  import axios from "axios";
  (async () => {
    let response = await axios({
      method: "post",
      url: 'https://api.turing.sh/audio/stt',
      headers: {
        "Content-Type": "application/json",
        Authorization: "Bearer YOUR_API_KEY",
        "x-captcha-token": "Captcha key"
      },
      data: {
  "model": "fast-whisper",
  "audio": "string",
  "type": "base"
},
    })
  })();
  ```
  ```python
  import requests
  import json
  response = requests.post(
    "https://api.turing.sh/audio/stt",
    headers={
      "Content-Type": "application/json",
      "Authorization": "Bearer YOUR_API_KEY",
      "x-captcha-token": "Captcha key"
    },
    data=json.dumps({
  "model": "fast-whisper",
  "audio": "string",
  "type": "base"
}),
  )
  ```
</CodeGroup>