RVC-Project/Retrieval-based-Voice-Conversion-WebUI
Easily train a good VC model with voice data <= 10 mins!
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
No releases in the last 90 days; the most recent was 105 days ago, with 1 contributor on GitHub.
Peaked at #88 in the weekly ranking the week of Sep 28, its best in the past year.
Use Cases & Benefits
- Enables training and real-time voice conversion models using minimal voice data and a user-friendly web interface.
- Offers fast training and inference even on modest GPUs with advanced pitch extraction to prevent voice leakage.
- Use for creating personalized voice conversion models from short audio samples for content creators.
- Use for real-time voice changing in live streaming or online communication with low latency support.
- Use for experimenting with voice style blending by merging multiple trained models to achieve unique timbres.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
MIT
Permissive: commercial use, modification and redistribution are allowed with attribution.
Community files
- README: present
Watch-outs
No watch-outs from GStars' checks.
General guidance from repository metadata, not legal advice. How we score
From the README
一个基于VITS的简单易用的变声框架
底模使用接近50小时的开源高质量VCTK训练集训练,无版权方面的顾虑,请大家放心使用
请期待RVCv3的底模,参数更大,数据更大,效果更好,基本持平的推理速度,需要训练数据量更少。
本仓库具有以下特点
点此查看我们的演示视频 !