---
title: Hi TTS
emoji: 🏢
colorFrom: yellow
colorTo: red
sdk: gradio
sdk_version: 5.46.0
app_file: app.py
pinned: false
short_description: Humanized Indic - TTS
---

# HI-TTS - Humanized Indic Text-to-Speech

A powerful Text-to-Speech system supporting 20+ Indic languages with advanced voice control features.

## Features

- 🌍 **Multi-language Support**: 20+ Indic languages including Hindi, Bengali, Telugu, Tamil, and more
- 🎭 **Voice Styles**: Multiple voice personalities (neutral, formal, casual, expressive, emotional)
- 🎛️ **Advanced Controls**: Pitch, speed, emotion, reverb, and background noise adjustment
- 🚀 **Real-time Generation**: Fast speech synthesis with customizable parameters
- 📱 **API Ready**: RESTful API for integration with mobile and web applications

## Supported Languages

- English (en)
- Hindi (hi) 
- Bengali (bn)
- Telugu (te)
- Marathi (mr)
- Tamil (ta)
- Gujarati (gu)
- Kannada (kn)
- Malayalam (ml)
- Odia (or)
- Punjabi (pa)
- Assamese (as)
- Bodo (brx)
- Dogri (doi)
- Konkani (gom)
- Maithili (mai)
- Manipuri (mni)
- Nepali (ne)
- Sanskrit (sa)
- Santali (sat)
- Sindhi (sd)
- Urdu (ur)
- Kashmiri (ks)
- Chhattisgarhi (hne)

## API Usage

### Endpoint: `/api/synthesize`

**Method:** POST

**Request Body:**
```json
{
  "text": "Your text here",
  "language": "en",
  "voice": "neutral",
  "pitch": 1.0,
  "speed": 1.0,
  "emotion": 0.5,
  "reverb": 0.0,
  "background_noise": 0.0
}
```

**Response:** 
- Audio file in WAV format

### Parameters

- `text`: Input text (max 1000 characters)
- `language`: Language code (default: "en")
- `voice`: Voice style ("neutral", "formal", "casual", "expressive", "emotional")
- `pitch`: Pitch control (0.5-2.0, default: 1.0)
- `speed`: Speed control (0.3-3.0, default: 1.0)
- `emotion`: Emotion intensity (0.0-1.0, default: 0.5)
- `reverb`: Reverb effect (0.0-1.0, default: 0.0)
- `background_noise`: Background noise level (0.0-1.0, default: 0.0)

## Usage

1. Enter your text in the text area
2. Select desired language
3. Choose voice style
4. Adjust voice parameters using sliders
5. Click "Generate Speech" to create audio
6. Download or play the generated speech

## License

This project is open source and available under the MIT License.

## Credits

Built on top of the Indic Parler-TTS model by AI4Bharat.