GPT-SoVITS
Few-shot voice cloning and TTS with a full training WebUI.
- Star 数
- 62.8K
- Fork 数
- 6.7K
- 未关闭 Issue
- 896
- 最近提交
- 2026-10-08
数据来自 GitHub API · 更新于 2026-10-15
GPT-SoVITS 是什么？
GPT-SoVITS clones a voice from about a minute of audio (or zero-shot from a few seconds) and supports Chinese, English, Japanese, Korean and Cantonese. Its WebUI bundles dataset tools — vocal separation, slicing, ASR labeling — and training.
主要功能
- Zero-shot and few-shot voice cloning
- Cross-lingual synthesis
- Dataset preparation tools in the WebUI
- Windows integrated package
系统要求
- 平台
- Windows · Linux · macOS
- 显卡
- NVIDIA recommended for training
- 显存
- 6 GB+
- Python
- 3.10
如何安装 GPT-SoVITS
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。
Windows integrated package
- 1Download the integrated package linked in the README and extract it.
- 2Double-click go-webui.bat to start the WebUI.
Linux / macOS
- 1Create an environment and run the install script described in the README.
git clone https://github.com/RVC-Boss/GPT-SoVITS.git cd GPT-SoVITS conda create -n GPTSoVits python=3.10 conda activate GPTSoVits bash install.sh - 2Start the WebUI.
python webui.py
优势
- Excellent quality with little data
- Strong for Chinese and Japanese
不足
- Complex UI with many steps
GPT-SoVITS 替代品对比
| 软件 | Star 数 | 许可证 | 平台 | 显存 |
|---|---|---|---|---|
| GPT-SoVITS Few-shot voice cloning and TTS with a full training WebUI. | 62.8K | MIT | 6 GB+ | |
| 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 | — | |
| RVC WebUI Retrieval-based voice conversion — train a voice model and convert singing or speech. | 38.7K | MIT | 4 GB+ | |
| Coqui TTS Deep-learning text-to-speech toolkit, including the XTTS voice cloning model. | 46.1K | MPL-2.0 | — | |
| Whisper OpenAI’s open-source speech recognition and translation model. | 110.5K | MIT | ~1 GB (tiny) to ~10 GB (large) |
常见问题
GPT-SoVITS 免费吗？
是的——GPT-SoVITS 是开源软件，采用 MIT 许可证。商用前请确认软件及模型权重的许可条款。
GPT-SoVITS 支持 Windows、Mac 和 Linux 吗？
GPT-SoVITS 支持：Windows, Linux, macOS。
运行 GPT-SoVITS 需要什么配置？
NVIDIA recommended for training. VRAM: 6 GB+
如何安装 GPT-SoVITS？
1. Download the integrated package linked in the README and extract it. 2. Double-click go-webui.bat to start the WebUI.
GPT-SoVITS 有哪些好的替代品？
常见替代品包括 Fish Speech, F5-TTS, RVC WebUI, Coqui TTS，详见本页对比表。