[samfriedman]

Free idea because I’m never going to get around to building it: An “AI 8 track” app; click record and hum a melody, then add a prompt and click generate. The model converts your input to an instrument matching your prompt, keeping the same notes/rhythm you hummed in the original. Record up to 8 tracks and do some simple mixing.

Would be a truly amazing thing for sketching songs! All you need is decent humming/singing/whistling pitch. Hum and generate a bass line, guitar lead, strings, etc. And then sing over it - would make solo musicians able to sketch out a song far easier than transcribing melody to a piano roll.

[xnx]

Google MusicLM (and probably lots of other tools) do this: "MusicLM .. can transform whistled and hummed melodies according to the style described in a text caption."

https://google-research.github.io/seanet/musiclm/examples/

[samspenc]

Sounds like Suno AI will soon have this feature as well https://x.com/suno_ai_/status/1794408506407428215

[ortusdux]

App name - Beat-it

https://www.youtube.com/watch?v=eZeYw1bm53Y

https://www.nme.com/blogs/nme-blogs/the-incredible-way-micha...

[eman2d]

A killer Ad would be converting each vocal track back into the original song

[michaelbrave]

the tech is technically there using 2-5 different AI solutions, it mostly lacks an interface that automatically takes one step to the next

[beoberha]

Facebook’s MusicGen can pretty much do this