GPT-SoVITS WebUI

This software is open source under the MIT license. The author does not have any control over the software. 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 the software package. See the root directory Agreement-LICENSE for details.

Model switch

GPT weight list

SoVITS weight list

*请上传并填写参考信息

Please upload a reference audio within the 3-10 second range; if it exceeds this duration, it will raise errors.

Recommended to use a Finetune-GPT when using Prompt-Free Mode.
If reference audio is not clear or unsure what to write, enable this option to ignore the reference text.

不填参考文本亦相当于开启, v3 does not support this mode currently, using it will cause an error.

开启无参考文本模式

Language for reference audio

Text for reference audio

Optional: Upload multiple reference audio files by dragging and dropping them (recommended to be of the same gender), and average their tone. If this option is left blank, the tone will be controlled by the single reference audio on the left. If fine-tuning the model, it is recommended that all reference audio files have tones within the fine-tuning training set; the pretrained model can be ignored.

*请填写需要合成的目标文本和语种模式

Inference text

Inference text languageLess Multilingual is better

How to slice the sentence

Adjust the speech rate and tone of the last synthesis result

Speech rate

0.6 1.65

Sentence Pause Duration

0.1 0.5

GPT sampling parameters

top_k

1 100

top_p

0 1

temperature

0 1

Inference Result