GPT-SoVITS

What GPT-SoVITS is

GPT-SoVITS is a free WebUI for few-shot voice conversion and text-to-speech. It can produce speech from a five-second vocal sample, or use one minute of training data to improve voice similarity and realism. Cross-lingual inference supports English, Japanese, Korean, Cantonese, and Chinese. Its WebUI includes tools for separating voice accompaniment, segmenting training sets automatically, multilingual speech recognition, and text labeling. Speech-recognition options include Fun-ASR-Nano, SenseVoice, classic FunASR, and Faster Whisper. The repository also provides an API with GET and POST inference endpoints that return WAV audio streams on success. Installation guidance covers Windows, Linux, and macOS, and Docker Compose services are documented in full and Lite variants. The Lite image does not include ASR or UVR5 models; UVR5 models need manual downloading, while ASR models download as needed. On macOS, the project temporarily uses CPUs because it reports significantly lower quality from models trained with Mac GPUs. GPT-SoVITS is released under the MIT License and links to Chinese and English user guides.