TTS · VOICE CLONING · MULTILINGUAL
Fish Speech
@FISHAUDIO
Use high-quality multilingual TTS to provide natural, clonable voice output for partners.
Fish Speech is aimed at high-quality speech generation and voice cloning, and can be used as a self-hosted mouth for companions to speak, read aloud and voice messages in real time.
Project address (can be copied to AI):https://github.com/fishaudio/fish-speech
PROJECT INTRO
Project introduction
Fish Speech is a multi-language generative TTS system that supports reference timbre cloning, long text speech generation, self-hosted inference and training, and provides command line, service interface and WebUI.
It is suitable for partner's voice reply, reading and voice message output; the code and model weights are currently subject to the Fish Audio Research License.
- Suitable for:Speech projects that value naturalness and multilingual capabilities, and can self-host GPU inference.
- Platform:Python with GPU self-hosted environment.
- Usage:Download the model, start the inference service or WebUI, and then call it from the companion front end.
- License:Fish Audio Research License, please check research and distribution boundaries before use.
COMMENTS & FEEDBACK
Comments and Feedback
People who have used this project can come back and tell newcomers: which platform it ran on, whether there were any pitfalls during the installation, and what the actual experience was like. The current version is in guest mode, and you do not need to register an account to leave a message.
The message is waiting for review and will be publicly displayed here after approval.
SOURCE & CREDIT
Atlas is responsible for the introduction and navigation, and the use still returns to the original author.
We do not mirror project files, nor do we intercept author traffic. For installation, download, version updates and the latest instructions, please refer to the project page provided by the original author.
Reading public comments...