the comfyui custom node for UVR5 to separate vocals and background music

AI Speech Solutions for Tasks such as ASR, Vocal Extraction, Accompaniment Extraction, Audio Denoising, and Enhancement, Support models such as paraformer, sensevoice, fireredasr, zipformer, moonshine, wenet, whisper, fsmn-vad, silero-vad, CT Transformer punc, Spleeter, Uvr5, etc, apply ONNX models in various scenarios.

Production-ready UVR5 CLI & Docker image. Run SOTA separation models (Roformer, SCNet, MDX, Demucs, VR Architecture) on headless GPU servers without dependency hell.

Docker image for TTS Generation ALL IN ONE

This repository contains all public UVR models, with possibly a few private ones included.

UVR5 Optimized for AMD Radeon (WINDOW11_ROCm 7.2) & Python 3.12. Patched dependencies (pyrubberband, playsound, Dora) for native acceleration. 4x faster than DirectML.

End-to-end voice cloning for Galgame/Visual Novel. One command: video URL -> multi-emotion character voices. Built on GPT-SoVITS v4.

An open-source, AI-powered karaoke platform and ad-free music player built on top of YouTube Music using Next.js, FastAPI, and UVR5 vocal separation.