Overview
GPT-SoVITS is a WebUI for few-shot voice cloning and text-to-speech. Its documented workflows include zero-shot synthesis from a short vocal sample, fine-tuning with a small training set, and cross-lingual inference for Chinese, English, Japanese, Korean, and Cantonese. It is designed to run locally with Python and PyTorch, and the WebUI includes dataset slicing, ASR, labeling, training, and inference utilities. The project code is released under the MIT license; model files and third-party components may have separate terms. It is aimed at local speech experiments and creator workflows.