1a1The users are not developers
The people who want this most are the least likely to be comfortable with a terminal, and a README that assumes any command-line familiarity excludes almost the entire audience.
0The facts
- Role
- Contributor
- Year
- 2026
- Status
- Live
- Category
- AI
- Built with
- Python · Audio source separation · Apple Silicon / MPS · CUDA · yt-dlp
- Where to find it
- Source
1 · Overview
What it is, and why it exists.
A free tool that strips music from videos on YouTube, Facebook and other sites while dialogue, narration and other sound keep playing, running against a local audio-separation backend on your own machine.
Made for people who avoid music for religious or personal reasons, and who currently have to choose between skipping useful content entirely or muting it and losing the speech too.
It runs a local separation backend on Apple Silicon or an NVIDIA GPU, with the CPU as a fallback, so the audio never leaves the machine. First-time setup takes about twenty minutes; starting it afterwards takes ten seconds.
1a · Challenges
Each problem got a card. Each fix got filed behind it.
1a1aWhat I did
The documentation assumes nothing. It explains where the Downloads folder is and what to click, step by step. Lowering the setup barrier mattered more here than any feature.
2 · Results
- Local-only music removal for streaming video, with Mac and Linux paths documented for non-technical users.
Next project
→cohere-transcribe
High-throughput Arabic/English transcription, batched properly.