GPT-SoVITS is an open-source speech and audio tool published on GitHub by RVC-Boss. With 63k stars on GitHub, it was last updated in October 2026. Related topics: text-to-speech, tts and vits.
“1 min voice data can also be used to train a good TTS model! (few shot voice cloning)”
— RVC-Boss, project description on GitHub
Details
| Category | Speech & Audio |
|---|---|
| GitHub stars | 63,129 |
| Forks | 6,711 |
| Language | Python |
| License | MIT |
| Last updated | |
| Owner | RVC-Boss |
| Repository | RVC-Boss/GPT-SoVITS |
Tags
text-to-speechttsvitsvoice-clonevoice-cloneaivoice-cloning
Repository facts from the GitHub public API, refreshed October 18, 2026. The quoted tagline is written by the project owner; the summary above is generated from public facts.