Task I want but have been too lazy - I have a favorite podcast, that I often fall asleep to. Certain parts with music etc. wake me up. I'd like to chop those parts out as automatically as possible. Can I do that here by e.g. giving some example edits to a few files, and asking to remove similar stuff from other files?
Sounds like something a better model armed with ffmpeg would already be able to do. Run an analysis on loudness along the track, detect when speech begins/ends (with whisper) around loud segments, and compress or cut those parts out
Hi, i finally feel confident enough to announce Audionaut. It's been 3-4 years in the making and my initial motivation was to edit my own multi-channel recordings with the old Sound Designer II workflow (create regions, drop to a playlist, export playlist, done). It got a little bigger now and the most current feature is the agent editing, which is imho very useful since you have the UI which always provides transparency.
To try the agent part with Claude Code (app and Node 18+ installed):
claude mcp add audionaut -- npx -y audionaut-mcp
Edits land in the open project as one undo step each, and saving stays with you. On macOS the app is sandboxed, so keep projects in ~/Music.
Concrats for finding the confidence. Looks really interesting. Put it on my list of projects to view during my down time. Thanks a ton for sharing. And congrats for getting something out the door.
To try the agent part with Claude Code (app and Node 18+ installed):
Edits land in the open project as one undo step each, and saving stays with you. On macOS the app is sandboxed, so keep projects in ~/Music.Downloads: https://audionaut.app/download.
any feedback is most appreciated