Flatsonar

Ultimate Vocal Remover

by minarru

Separate vocals and instruments from audio using AI models

Dangerous permissions Unverified publisher MIT vv1.2.0
Install Source code

About

Ultimate Vocal Remover is a desktop application for AI-powered audio source separation. It splits a song into stems (vocals, instrumental, drums, bass and more) using VR, MDX-Net and Demucs models, with optional ensembling and GPU acceleration.

Permissions

1 permission weaken the sandbox. Flatsonar asks before installing.

  • all devices (/dev): webcams, disks, raw hardware
    --device=all
  • Wayland display
    --socket=wayland
  • X11 display, only when Wayland is unavailable
    --socket=fallback-x11
  • inter-process communication (needed for X11)
    --share=ipc
  • GPU acceleration
    --device=dri
  • audio
    --socket=pulseaudio
  • network
    --share=network

Who publishes this

Nobody has confirmed that the publisher controls this app id. Flatsonar warns before installing.

  • org.uvr.UltimateVocalRemover claims the domain uvr.org; only its owner can prove that
    publisher:namespace

Maintenance

Recent activity on the upstream repository, or built and reviewed by Flathub.

No staleness signals: recent activity, or built and reviewed by Flathub.