stemrollerapp/stemroller
Isolate vocals, drums, bass, and other instrumental stems from any song
Built on Facebook's Demucs deep learning model for source separation, it integrates YouTube search to fetch audio directly within the app, enabling offline stem extraction without manual file uploads. The cross-platform desktop application (Windows/macOS/Linux) bundles ffmpeg and yt-dlp dependencies, processing audio locally to separate vocals, drums, bass, and other instrumental tracks in a single workflow.
3,052 stars.
Stars
3,052
Forks
153
Language
Svelte
License
—
Category
Last pushed
Feb 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/stemrollerapp/stemroller"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
lucidrains/HS-TasNet
Implementation of HS-TasNet, "Real-time Low-latency Music Source Separation using Hybrid...
justinsalamon/scaper
A library for soundscape synthesis and augmentation
tsurumeso/vocal-remover
Vocal Remover using Deep Neural Networks
thepirat000/spleeter-api
Audio separation API using Spleeter from Deezer
gitmylo/audio-webui
A webui for different audio related Neural Networks