Fish Speech

The demo in this space is version 1.5, Please check Fish Audio for the best model.

该 Demo 为 Fish Speech 1.5 版本, 请在 Fish Audio 体验最新 DEMO.

A text-to-speech model based on VQ-GAN and Llama developed by Fish Audio.
由 Fish Audio 研发的基于 VQ-GAN 和 Llama 的多语种语音合成.

You can find the source code here and models here.
你可以在 这里 找到源代码和 这里 找到模型.

Related code and weights are released under CC BY-NC-SA 4.0 License.
相关代码，权重使用 CC BY-NC-SA 4.0 许可证发布.

We are not responsible for any misuse of the model, please consider your local laws and regulations before using it.
我们不对模型的任何滥用负责，请在使用之前考虑您当地的法律法规.

The model running in this WebUI is Fish Speech V1.5 Medium. 在此 WebUI 中运行的模型是 Fish Speech V1.5 Medium.