GPT-SoVITS-ProPlus Zero-shot TTS Demo

https://github.com/RVC-Boss/GPT-SoVITS

Input 3 to 10s reference audio to guide the time-bre, speed, emotion of voice, and generate the speech you want by input the inference text.
输入3至10秒的参考音频来引导待合成语音的音色、语速和情感,然后输入待合成目标文本,生成目标语音.
Cross-lingual Support: Inference in languages different from the training dataset, currently supporting English, Japanese, Korean and Cantonese.
目前支持中日英韩粤跨语种混合合成。
If the quota has been reached, you can try the backup space at https://huggingface.co/spaces/XXXXRT/GPT-SoVITS-ProPlus
如果遇到限额不够可以去备用空间https://huggingface.co/spaces/XXXXRT/GPT-SoVITS-ProPlus 试试
This demo is open source under the MIT license. The author does not have any control over it. Users who use the software and distribute the sounds exported by the software are solely responsible. If you do not agree with this clause, you cannot use or reference any codes and files within this demo.
本demo以MIT协议开源, 作者不对软件具备任何控制力, 使用软件者、传播软件导出的声音者自负全责. 如不认可该条款, 则不能使用或引用该demo内的任何代码和文件.

*Please upload and fill reference information

Language for reference audio

*Please fill in the target text and language mode for synthesis

Inference text languageThe smaller the range, the better the performance.
How to slice the sentence

Adjust speech rate, higher for faster

0.6 1.65

GPT sampling parameters (not too low when there's no reference text. Use default if unsure):

1 100
0 1
0 1