2.3.260718

RVC-Project/Retrieval-based-Voice-Conversion-WebUI2.3.260718Jul 21, 2026by RVC-Boss

AI Summary

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.

Key Highlights

  • FCPE pitch extraction algorithm support
  • Real-time VST2/VST3 Plugin support
  • Backend switch from UVR5 to PyMSS for vocal separation
  • CUDA Graph acceleration for real-time mode (up to 4.7x speedup)
  • GPU auto-detection for inference mode and precision

New Features

  • FCPE pitch extraction algorithm
  • Real-time VST2/VST3 Plugin
  • PyMSS vocal separation backend
  • CUDA Graph acceleration
  • GPU-based audio resampling

Full Release Notes

### 完整包 Complete package

For Nvidia GPU users (<50x0):
https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/RVC20260718Nvidia.7z

For Nvidia GPU users (>=50x0):
https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/RVC20260718Nvidia50x0.7z

For AMD/Intel GPU users:
https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/RVC20260718AMD_Intel.7z

RVC Real-Time VST2/VST3 Plugin (For user instructions, please refer to the README included in the archive. You should unzip the complete package first.)
https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/RVCRealtime-Win64VST.zip

中国用户可使用以下2个源加速下载
1、免费满速下载直链合集:https://www.yuque.com/flowercry/hxf0ds
2、度盘需要超级会员才可不限速下载
链接:https://pan.baidu.com/s/16BHeTXRq2aGUzDZo1BY1Lw 
提取码: tvy6 

Changelog [(English verison)](https://github.com/liujing04/Retrieval-based-Voice-Conversion-WebUI/blob/main/docs/en/Changelog_EN.md):

降低网页使用难度(推理输入音频无需输入路径,前端实时日志优化,保存推理用小模型后自动刷新模型列表,推理首页选择模型后自动检测匹配的index路径等)

数据特征提取、训练模型、索引阶段可中途掐断,重启继续进度

GPU自动识别判断推理模式和精度

修复依赖问题(例如pyworld,fairseq,matplotlib,pyav,onnxruntime-gpu环境修复等)

解决编码问题

网页启动自动探寻可用端口

单卡训练不用DDP

基础模型不变,若干影响效果的修复,使用现有微调模型更新整合包/代码包版本重新推理,或者使用新版本重新训练再推理,均有可能效果会有提升。

支持FCPE音高提取算法

实时变声模式gui支持cuda graph推理加速,算法推理延时指标最高加速4.7倍(4090D测试结果),同时显卡占用相对降低20~30%左右

移除了已明显无用或过时的功能

人声与伴奏分离后端由 UVR5 更换为 PyMSS,并支持推理时中断 (更好的人声分离算法能显著提高推理效果)

优化输入音频的读取与重采样流程,在条件允许时使用 GPU 处理,以提高推理效率并降低 CPU 占用

修复 Windows 环境下训练进程的 libuv 兼容问题