GPT-SoVITS
A powerful zero-shot voice conversion and text-to-speech WebUI.
CommonProductProductivityVoice ConversionText-to-Speech
GPT-SoVITS-WebUI is a powerful zero-shot voice conversion and text-to-speech WebUI. It features zero-shot TTS, few-shot TTS, cross-language support, and a WebUI toolkit. The product supports English, Japanese, and Chinese, providing integrated tools such as voice accompaniment separation, automatic training set splitting, Chinese ASR, and text annotation to help beginners create training datasets and GPT/SoVITS models. Users can experience real-time text-to-speech conversion by inputting a 5-second voice sample, and they can fine-tune the model using only 1 minute of training data to improve voice similarity and naturalness. The product supports environment setup, Python and PyTorch versions, quick installation, manual installation, pre-trained models, dataset formats, pending tasks, and acknowledgments.
GPT-SoVITS Visit Over Time
Monthly Visits
488643166
Bounce Rate
37.28%
Page per Visit
5.7
Visit Duration
00:06:37