Ultimate Vocal Remover
A free, open-source desktop vocal remover separates audio locally on Windows, macOS and Linux with MDX-Net and Demucs models.
Ultimate Vocal Remover separates vocals and other parts of songs on your computer. It's for people preparing karaoke tracks or isolating audio for music projects.
- Vocal separation. Remove vocals from a recording or isolate them from the accompanying music.
- Four-stem separation. Demucs models split recordings into four stems for working with individual parts of a song.
- Model choice. The desktop interface supports MDX-Net and Demucs, so you can use different separation models for your audio.
- GPU acceleration. Compatible NVIDIA GPUs can accelerate processing, while Apple M1 GPU support covers Demucs v4 and all MDX-Net models.
The app is free and open source under the MIT license. Windows bundles target Windows 10 or later, and Mac bundles target macOS Big Sur or later. Linux support includes Debian and Arch-based systems.
NVIDIA GPU processing requires at least a GTX 1060 with 6 GB of VRAM; 8 GB or more is recommended. AMD Radeon support is limited. WAV processing works without FFmpeg, but other audio formats require it.
Logotyper
