Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine
| Date | Stars |
|---|---|
| 2026-07-24 | 713 |
| 2026-07-25 | 714 |
| 2026-07-28 | 714 |
| 2026-07-30 | 714 |
| 2026-08-06 | 714 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
<img src="https://2901733926.github.io/Confucius4-TTS/Confucius4-TTS.jpg" alt="Confucius4-TTS" width="35%">
<h1>Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine</h1>
<p><b>One voice. Any language.</b></p>
</div>
<div align="center">
<a href="./README.zh.md"><img src="https://img.shields.io/badge/README-中文版本-red"></a>
<a href="./LICENSE"><img src="https://img.shields.io/badge/code_license-Apache%202.0-blue"></a>
<a href="https://confucius4-tts.youdao.com/gradio"><img src="https://img.shields.io/badge/Demo-在线体验-orange"></a>
<a href="https://2901733926.github.io/Confucius4-TTS/"><img src="https://img.shields.io/badge/GitHub.io-Demo_Page-blue?logo=GitHub&style=flat-square"></a>
<a href="https://huggingface.co/netease-youdao/Confucius4-TTS"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Confucius4TTS-yellow"></a>
<a href="https://modelscope.cn/models/netease-youdao/Confucius4-TTS"><img src="https://img.shields.io/badge/ModelScope-Confucius4TTS-purple"></a>
</div>
<br>
Confucius4-TTS is an advanced LLM-based text-to-speech (TTS) system designed for multilingual and cross-lingual speech synthesis. Built on a speech encoder + large language model (LLM) architecture, Confucius4-TTS enables high-quality speech generation while preserving speaker identity across languages. You can try our online demo at **[https://confucius4-tts.youdao.com/gradio](https://confucius4-tts.youdao.com/gradio)**.
**✨ Key Features**
- **14 Languages Supported**: Chinese, English, Japanese, Korean, German, French, Spanish, Indonesian, Italian, Thai, Portuguese, Russian, Malay and Vietnamese *(more coming soon)*
- **Unconstrained Voice Cloning**: No reference transcript required
- **Cross-Lingual Voice Transfer**: Unaccented speech synthesis across 14 languages
- **Zero-Shot Voice Transfer**: Clone voices without additional training
- **Seamless Emotion Transfer**: Clone the feeling, not just the voice
- **Robust Generalization**: Stable performance in real-world multilingual scenarios
With strong cross-lingual generalization, Confucius4-TTS allows users to seamlessly switch languages while keeping the same voice, delivering fluent, natural, and expressive speech.
<div align="center">
Video Demo
<table border="0">
<tr>
<td>
<video src="https://github.com/user-attachments/assets/2e2a4fc2-c8ef-4f12-89f7-55a6221200f1" controls width="100%"></video>
</td>
<td>
<video src="https://github.com/user-attachments/assets/dacd356d-3bf5-4b06-9a2c-6ad5c24eb035" controls width="100%"></video>
</td>
</tr>
<tr>
<td>
<video src="https://github.com/user-attachments/assets/e00ae5e1-fbb0-4137-af13-dd53599196a5" controls width="100%"></video>
</td>
<td>
<video src="https://github.com/user-attachments/assets/f6c1aabb-4258-40ba-b945-81c3eeed67c3" controls width="100%"></video>
</td>
</tr>
</table>
</div>
## Contents
- [Installation](#-installation)
- [Inference](#-inference)
- [Training](#-training)
- [Performance](#-performance)
- [Citation](#citation)
## 🛠 Installation
### Requirements
- Python 3.10
- CUDA 12.6
### Setup
1. Clone the repository:
```bash
git clone https://github.com/netease-youdao/Confucius4-TTS.git
cd Confucius4-TTS
```
2. Create and activate a conda environment:
```bash
conda create -n confuciustts python=3.10 -y
conda activate confuciustts
```
3. Install dependencies:
```bash
pip install -r requirements.txt
```
## 🚀 Inference
For environments with restricted access to HuggingFace, set a mirror endpoint before running:
```bash
export HF_ENDPOINT=https://hf-mirror.com
```
### Basic Usage
Use the provided `example.py` script for zero-shot TTS synthesis:
```bash
python example.py \
--prompt_wav path/to/referExcerpt of 16,330 characters
Read on GitHub
25
5
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:0a2f41ea89729a64, topic:text-to-speech, topic:tts, topic:speech-synthesis
matched fp:0a2f41ea89729a64, topic:deep-learning, topic:pytorch