ChatTTS

<div align="center">

<a href="https://trendshift.io/repositories/10489" target="_blank"><img src="https://trendshift.io/api/badge/repositories/10489" alt="2noise%2FChatTTS | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>

# ChatTTS
A generative speech model for daily dialogue.

[![Licence](https://img.shields.io/github/license/2noise/ChatTTS?style=for-the-badge)](https://github.com/2noise/ChatTTS/blob/main/LICENSE)
[![PyPI](https://img.shields.io/pypi/v/ChatTTS.svg?style=for-the-badge&color=green)](https://pypi.org/project/ChatTTS)

[![Huggingface](https://img.shields.io/badge/🤗%20-Models-yellow.svg?style=for-the-badge)](https://huggingface.co/2Noise/ChatTTS)
[![Open In Colab](https://img.shields.io/badge/Colab-F9AB00?style=for-the-badge&logo=googlecolab&color=525252)](https://colab.research.google.com/github/2noise/ChatTTS/blob/main/examples/ipynb/colab.ipynb)
[![Discord](https://img.shields.io/badge/Discord-7289DA?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/Ud5Jxgx5yD)

**English** | [**简体中文**](docs/cn/README.md) | [**日本語**](docs/jp/README.md) | [**Русский**](docs/ru/README.md) | [**Español**](docs/es/README.md) | [**Français**](docs/fr/README.md) | [**한국어**](docs/kr/README.md)

</div>

## Introduction
> [!Note]
> This repo contains the algorithm infrastructure and some simple examples.

> [!Tip]
> For the extended end-user products, please refer to the index repo [Awesome-ChatTTS](https://github.com/libukai/Awesome-ChatTTS/tree/en) maintained by the community.  
> You can find a diagram visualization of the codebase [here](https://github.com/CodeBoarding/GeneratedOnBoardings/blob/main/ChatTTS/on_boarding.md).

ChatTTS is a text-to-speech model designed specifically for dialogue scenarios such as LLM assistant.

### Supported Languages
- [x] English
- [x] Chinese
- [ ] Coming Soon...

### Highlights
> You can refer to **[this video on Bilibili](https://www.bilibili.com/video/BV1zn4y1o7iV)** for the detailed description.

1. **Conversational TTS**: ChatTTS is optimized for dialogue-based tasks, enabling natural and expressive speech synthesis. It supports multiple speakers, facilitating interactive conversations.
2. **Fine-grained Control**: The model could predict and control fine-grained prosodic features, including laughter, pauses, and interjections. 
3. **Better Prosody**: ChatTTS surpasses most of open-source TTS models in terms of prosody. We provide pretrained models to support further research and development.

### Dataset & Model
> [!Important]
> The released model is for academic purposes only.

- The main model is trained with Chinese and English audio data of 100,000+ hours.
- The open-source version on **[HuggingFace](https://huggingface.co/2Noise/ChatTTS)** is a 40,000 hours pre-trained model without SFT.

### Roadmap
- [x] Open-source the 40k-hours-base model and spk_stats file.
- [x] Streaming audio generation.
- [x] Open-source DVAE encoder and zero shot inferring code.