Retrieval-based-Voice-Conversion-WebUI Releases
8 releases of RVC-Project/Retrieval-based-Voice-Conversion-WebUI
- 2.3.260718
A major update focusing on performance improvements, algorithm upgrades including FCPE pitch extraction, and a backend switch from UVR5 to PyMSS for better vocal separation. Also introduces CUDA Graph acceleration for real-time mode.
Jul 21, 2026
- 2.2.231006
Optimizes the go-realtime-gui interface and improves RMVPE pitch extraction, specifically benefiting low male voices. Adds new parameters for better control over the output.
Jun 5, 2024
- 2.1.230814
This release introduces the RMVPE pitch extraction model - the strongest open-source vocal pitch extraction model - and adds AMD/Intel GPU support through pytorch-dml. Multiple bug fixes and quality-of-life improvements are included.
Jun 5, 2024
- 2.0.230618
This major update adds 32k and 48k pretrained models, fixes inference errors for non-f0 models, and introduces ONNX export capability. Performance optimizations for large datasets are also included.
Jun 5, 2024
- 2.0.230528
This release introduces v2 model support with improved voice quality protection and adds the crepe-full pitch detection model. UVR5 vocal/instrument separation is enhanced with dereverb and de-echo models.
Jun 5, 2024
- 1.2.230428
This release improves faiss index performance and removes GPU limitations. Bug fixes for UVR5 and expanded mini-GUI support are included.
Jun 5, 2024
- 1.1.230416
Significant training improvements including fixes for GPU utilization and batch size logic. Introduces a local real-time GUI and multi-language support for the WebUI.
Jun 5, 2024
- 1.0.230410
Initial release (v1.0) of the Retrieval-based-Voice-Conversion-WebUI. Includes base package and updated package instructions.
Jun 5, 2024