F5-TTS
Zero-shot voice cloning TTS based on flow matching.
- Star 数
- 15.4K
- Fork 数
- 2.2K
- 未关闭 Issue
- 63
- 最近提交
- 2026-10-14
数据来自 GitHub API · 更新于 2026-10-15
F5-TTS 是什么？
F5-TTS generates natural speech in the voice of a short reference clip without training. It ships a pip package with a Gradio app and CLI, and supports multi-speaker dialogue and speed control.
主要功能
- Zero-shot voice cloning from seconds of audio
- Gradio app and CLI
- Multi-style / multi-speaker generation
系统要求
- 平台
- Windows · macOS · Linux
- 显卡
- NVIDIA recommended; Apple Silicon supported
- Python
- 3.10+
如何安装 F5-TTS
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。
pip
- 1Install PyTorch for your device, then F5-TTS.
pip install f5-tts - 2Launch the web app.
f5-tts_infer-gradio
优势
- High-quality cloning with no training
- Simple install
不足
- Pretrained weights are CC-BY-NC (non-commercial)
F5-TTS 替代品对比
| 软件 | Star 数 | 许可证 | 平台 | 显存 |
|---|---|---|---|---|
| F5-TTS Zero-shot voice cloning TTS based on flow matching. | 15.4K | MIT | — | |
| Fish Speech Multilingual TTS and voice cloning from Fish Audio. | 33.1K | Apache-2.0 | 4 GB+ | |
| GPT-SoVITS Few-shot voice cloning and TTS with a full training WebUI. | 62.8K | MIT | 6 GB+ | |
| Kokoro A tiny 82M-parameter TTS model with surprisingly natural voices. | 9.3K | Apache-2.0 | — | |
| 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
F5-TTS 免费吗？
是的——F5-TTS 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。
F5-TTS 支持 Windows、Mac 和 Linux 吗？
F5-TTS 支持：Windows, macOS, Linux。
运行 F5-TTS 需要什么配置？
NVIDIA recommended; Apple Silicon supported
如何安装 F5-TTS？
1. Install PyTorch for your device, then F5-TTS. 2. Launch the web app.
F5-TTS 有哪些好的替代品？
常见替代品包括 Fish Speech, GPT-SoVITS, Kokoro, Coqui TTS，详见本页对比表。