GPT-SoVITS (Voice Cloning)
Few-shot voice cloning and TTS using GPT and SoVITS architectures.
About
GPT-SoVITS is a few-shot voice cloning and text-to-speech WebUI that pairs a GPT-style language model with the SoVITS synthesis architecture. It can clone a voice from a five-second sample and supports fine-tuning on about a minute of audio for closer matches. Cross-lingual synthesis covers Chinese, English, Japanese, Korean, and Cantonese. Released by RVC-Boss under the MIT license with a WebUI and Colab notebook.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Voice Cloning & Voice Conversion
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- AGPL-3.0
- Minimum VRAM
- 6 GB
- Added
- Apr 3, 2026
Related Tools
Zero-shot voice cloning mode of CosyVoice model by Alibaba.
Community fork of RVC with additional features and optimizations.
Updated zero-shot voice cloning by MyShell with improved quality.
Voice cloning mode of XTTS-v2 for creating custom voice replicas.
Zero-shot voice cloning capabilities of Fish Speech model.
Easy-to-use voice conversion framework based on retrieval for real-time voice cloning.