Fish Speech
Multilingual TTS and voice cloning from Fish Audio.
- Star 数
- 33.1K
- Fork 数
- 2.9K
- 未关闭 Issue
- 16
- 最近提交
- 2026-10-14
数据来自 GitHub API · 更新于 2026-10-15
Fish Speech 是什么？
Fish Speech (OpenAudio) is a multilingual text-to-speech system with zero-shot voice cloning and emotion control. It provides a WebUI, API server and Docker images.
主要功能
- Zero-shot voice cloning
- Strong Chinese, English and Japanese support
- WebUI and HTTP API server
系统要求
- 平台
- Linux · Windows · Docker
- 显卡
- NVIDIA
- 显存
- 4 GB+
- Python
- 3.10+
如何安装 Fish Speech
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/fishaudio/fish-speech.git cd fish-speech pip install -e . - 2Download the checkpoints and start the WebUI as described in the docs.
优势
- Excellent multilingual quality
- Server mode for apps
不足
- Model weights are licensed for non-commercial use
Fish Speech 替代品对比
| 软件 | Star 数 | 许可证 | 平台 | 显存 |
|---|---|---|---|---|
| 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 | — | |
| 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 | — | |
| 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
Fish Speech 免费吗？
是的——Fish Speech 是开源软件，采用 Apache-2.0 许可证。商用前请确认软件及模型权重的许可条款。
Fish Speech 支持 Windows、Mac 和 Linux 吗？
Fish Speech 支持：Linux, Windows, Docker。
运行 Fish Speech 需要什么配置？
NVIDIA. VRAM: 4 GB+
如何安装 Fish Speech？
1. Clone and install. 2. Download the checkpoints and start the WebUI as described in the docs.
Fish Speech 有哪些好的替代品？
常见替代品包括 F5-TTS, GPT-SoVITS, Kokoro, Whisper，详见本页对比表。