#5 · Primary category: AI Music Generation
stemroller
Isolate vocals, drums, bass, and other instrumental stems from any song
Project last updated:06/30/26
GitHub Stars
3.2K
Forks
157
Contributors
8
License
Other
Why we included this project
StemRoller is a desktop app that puts Facebook's Demucs model behind a single button, so you don't have to touch the Python command line to pull a song apart into vocals, drums, bass, and everything else. Type a track name into the built-in YouTube search, hit Split, wait a few minutes, and the stems come back as files you can open right away. That makes it a fast route to stems for remixing or karaoke without hunting down a local audio file first. The whole thing is free and open source, so anyone who wants to tweak the workflow or bundle their own models can build from the released code.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
muzic
Muzic: Music Understanding and Generation with Artificial Intelligence
ace-step-ui
🎵 The Ultimate Open Source Suno Alternative - Professional UI for ACE-Step 1.5 AI Music Generation. Free, local, unlimited. Stop paying for Suno!
suno-api
Use API to call the music generation AI of suno.ai, and easily integrate it into agents like GPTs.
riffusion-hobby
Stable diffusion for real-time music generation
ableton-mcp
🎵 Control Ableton Live with Claude AI — create tracks, arrange clips & compose music via MCP