ChatTTS
Conversational TTS for dialogue, with laughter and pauses.
- Star 数
- 39.9K
- Fork 数
- 4.3K
- 未关闭 Issue
- 63
- 最近提交
- 2026-04-10
数据来自 GitHub API · 更新于 2026-10-15
ChatTTS 是什么？
ChatTTS is optimized for dialogue-style speech in Chinese and English and can insert prosodic features such as laughter and pauses, making it well-suited to LLM assistants.
主要功能
- Dialogue-optimized prosody
- Fine-grained control tokens ([laugh], [uv_break])
- Chinese and English
系统要求
- 平台
- Windows · macOS · Linux
- 显卡
- NVIDIA recommended
- 显存
- 4 GB+
如何安装 ChatTTS
根据项目 README 整理。开源项目更新很快，请以 GitHub 页面上的最新说明为准。
From source
- 1Clone and install.
git clone https://github.com/2noise/ChatTTS cd ChatTTS pip install --upgrade -r requirements.txt - 2Start the web demo.
python examples/web/webui.py
优势
- Very natural conversational speech
不足
- Weights are non-commercial
- Limited languages
ChatTTS 替代品对比
| 软件 | Star 数 | 许可证 | 平台 | 显存 |
|---|---|---|---|---|
| ChatTTS Conversational TTS for dialogue, with laughter and pauses. | 39.9K | AGPL-3.0 | 4 GB+ | |
| Kokoro A tiny 82M-parameter TTS model with surprisingly natural voices. | 9.3K | Apache-2.0 | — | |
| Fish Speech Multilingual TTS and voice cloning from Fish Audio. | 33.1K | Apache-2.0 | 4 GB+ | |
| F5-TTS Zero-shot voice cloning TTS based on flow matching. | 15.4K | MIT | — | |
| Whisper OpenAI’s open-source speech recognition and translation model. | 110.5K | MIT | ~1 GB (tiny) to ~10 GB (large) | |
| whisper.cpp Whisper in plain C/C++ — fast on CPUs, Apple Silicon and mobile. | 54.4K | MIT | — |
常见问题
ChatTTS 免费吗？
是的——ChatTTS 是开源软件，采用 AGPL-3.0 许可证。商用前请确认软件及模型权重的许可条款。
ChatTTS 支持 Windows、Mac 和 Linux 吗？
ChatTTS 支持：Windows, macOS, Linux。
运行 ChatTTS 需要什么配置？
NVIDIA recommended. VRAM: 4 GB+
如何安装 ChatTTS？
1. Clone and install. 2. Start the web demo.
ChatTTS 有哪些好的替代品？
常见替代品包括 Kokoro, Fish Speech, F5-TTS, Whisper，详见本页对比表。