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
Downloads: https://audionaut.app/download.
any feedback is most appreciated
Congrats on the launch!
I tried to built something similar in go and wails but quickly hit roadblock with some critical features that required high time precision.
I wonder if I could use it for my use case, do you have any roadmap?
i have a backlog but no roadmap. audionaut is very precise when it comes to timing if that's what you mean or what's your use case?
My use case is pretty unique I guess and not something you built audionaut for. I do small live gigs in a local place where I sometimes need to operate lights, screen and play music at the same time and need something I can cue things to multiple software/devices through osc, websocket, tcp during music playback. I know there is already software for that but I didn't find anything I could run and quickly operate during the rehearsal before the event.
I was just wondering if you planed to add some features like markers or cue for integrations.
to be honest i was not planning to add features like that but it's very tempting. Supporting OSC is easy but a proper and useful mapping of parameters will take more brain work. i used OSC way back with PD and Reaktor.. the network layer adds latency with is ok with video sync... i have to revisit, it's years back.
thanks for your feedback, i added this topic to my backlog.
This is something that I’m interested in as well. My wife generally uses QLab for this and gets a lot of mileage out of it, but often enough ends up wanting this or that extra feature that just isn’t there.
I’m not sure that integrating it into a DAW is the way to go, but there’s definitely a need there.
You want REAPER
I actually use Reaper a lot for something else and tried to use it for gigs too but Reaper seems to be able only to receive osc commands, couldnt find a way to send any. I think its possible to write custom cpp extension for that but cpp is not my comfort zone.
Does it edit music/podcasts automatically, or still needs a human proxy? If it does automatically, how does AI know when to stop?
you could edit anything automatically. import -> analyse -> auto edit -> assemble -> export. this what the prototype in python used to do. the result however often needs small edits and audionaut's UI is supposed to help with that.