Audionaut demo: Claude cuts a song every 16 bars, splits the clips across two tracks and closes the gaps, then sets crossfades and a fade-out, while the user runs Auto Edit and stem separation in the app

Picture published by the creator on GitHub.

Edit and record multitrack audio, and let an AI agent make the cuts

Made by Klaus Voltmer

Audionaut is a free desktop audio editor for music, podcasts and multitrack recordings: cut audio into regions, arrange them in per-track playlists, add crossfades and export, without the weight of a full music studio app.

It is written in C++ on JUCE (a common audio-app framework) and runs on Windows, macOS and Linux. It also speaks MCP (a connector for AI assistants), so Claude can edit an open session while you watch, each edit landing as one undo step. It can analyse beats, auto-edit and split a song into drums, bass, vocals and other stems.

Can I use this?

Mac, Windows or Linux app

You'll need A Mac, Windows or Linux computer · Free download; Node.js 18+ for the optional AI connector

Worth knowing Licensed GPL-3.0 or later, with a commercial license the creator says is not yet available. Stem separation downloads Meta's Demucs model weights on first use, which Meta says are for scientific purposes only. The creator says it is not a full studio app yet: plug-in effects are still on the backlog. On a Mac the app is sandboxed, so keep projects in your Music folder. Anonymous usage statistics are opt-in. BuildTube has not run or verified this software.

Why it's here

229 people have starred it on GitHub.
Shown on Hacker News (Show HN) on 2 October, with 152 points.

Numbers as of 6 October 2026, from BuildTube’s latest daily refresh.

Behind it

See the code on GitHub

BuildTube has not run or verified this project. Everything above is written from what the creator published.

Made this?