# Speech to Text

> Speech-to-Text transforms audio into written transcription, allowing spoken language to be converted into text for various applications.

## Overview

- **Model ID**: `speech-to-text`
- **Category**: audio
- **Provider**: modelslab
- **Status**: active
- **Screenshot**: `https://assets.modelslab.com/generations/f2534f26-caa0-4c9c-ac06-70666a0ff414.webp`

## API Information

This model can be used via our HTTP API. See the API documentation and usage examples below.

### Endpoint

- **URL**: `https://modelslab.com/api/v6/voice/speech_to_text`
- **Method**: POST

### Parameters

- **`init_audio`** (required): The URL of the audio file to be transcribed. Supported formats: WAV, MP3,FLAC, OPUS. min: 5 seconds - max: 1 hour.
  - Type: file ("audio/mp3,audio/wav")
  - Example: Enter Audio URL

- **`language`** (optional): The language code of the audio content in ISO 639-1 format (e.g. 'en' for English, 'es' for Spanish).	
  - Type: select (options: English)
  - Example: Language

## Usage Examples

### cURL

```bash
curl --request POST \
  --url https://modelslab.com/api/v6/voice/speech_to_text \
  --header "Content-Type: application/json" \
  --data '{
    "key": "YOUR_API_KEY",
    "model_id": "speech-to-text",
    "init_audio": "https://pub-f3505056e06f40d6990886c8e14102b2.r2.dev/audio/tom_hanks_1.wav",
    "language": "en"
  }'
```

### Python

```python
import requests

response = requests.post(
    "https://modelslab.com/api/v6/voice/speech_to_text",
    headers={
        "Content-Type": "application/json"
    },
    json={
        "key": "YOUR_API_KEY",
        "model_id": "speech-to-text",
        "init_audio": "https://pub-f3505056e06f40d6990886c8e14102b2.r2.dev/audio/tom_hanks_1.wav",
        "language": "en"
    }
)

print(response.json())
```

### JavaScript

```javascript
fetch("https://modelslab.com/api/v6/voice/speech_to_text", {
  method: "POST",
  headers: {
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "key": "YOUR_API_KEY",
    "model_id": "speech-to-text",
    "init_audio": "https://pub-f3505056e06f40d6990886c8e14102b2.r2.dev/audio/tom_hanks_1.wav",
    "language": "en"
  })
})
.then(response => response.json())
.then(data => console.log(data));
```

## Links

- [Model Playground](https://modelslab.com/models/speech-to-text/speech-to-text)
- [API Documentation](https://docs.modelslab.com)
- [ModelsLab Platform](https://modelslab.com)