What is the use case for music generation models? I see usecases for alot of the other foundation models like text, image, tts, sst, but why do I want AI generated music?
I’ve mostly used them for laughs with my friends. Sometimes generating “custom” songs with funny lyrics, but most fun so far is editing lyrics of existing songs to say ridiculous things for fun.
No real clue how someone would use them for a more serious endeavor, only thing I could imagine would be to quickly iterate/prototype with song structures on a fixed seed to generate ideas for a real composition. Consider the case of an indie game developer or film maker getting some placeholder music to test the experience during early throwaway iterations.
A major subset is people pretending to be musicians but not care to make music themselves. They just want the title for free. That's the demographic that used loops off of Splice (not even crate digging) + note generators and such and called it a day.
Another more valid subset would be something like a music bed for a video or podcast etc.
A third use is for spamming streaming platforms and making money off undiscerning suckers.
In order to make better ai tools for generating specific parts of a song, you ideally want models that understand what good music sounds like when put together. These sorts of "generate whole songs" are a predecessor to more specific tooling. These tools are slowly moving downstream (look at the evolution of Suno) and will almost certainly eventually move to a place where they are just a part of the music production workflow. We increasingly have improved tools to break down full tracks into stems, stems to/from midi/lyrics.
Lots of potential musicians / producers that can write a catchy tune, lyrics, create midi work, etc; but maybe can't play / don't own the instruments they want to use (could be disabled) or maybe don't have a great singing voice. These ai tools can lower the bar for more people to create music at a higher level. It can also act as a improvisational partner, to explore more musical space faster.
As a personal anecdote of where AI might be useful, as a hobby I occasionally participate in game jams, sometimes working on music / sound effects to stretch my legs form my day job. One game jam game I worked on was inspired by a teammates childhood in Poland. So I listened to a bunch of traditional Polish music and created a track inspired by said music. I'm pretty happy with how it came out, but with current AI I'm sure I could have improved the results significantly. If I were to be making it now, I would be able to upload the tracks I wrote, see how the AI might bring it closer to something that sounds authentic, and using that to help me rewrite parts of the melody where it was lacking. Then I could have piped in my final melody with it's inauthentic midi instrument (I neither own, nor play traditional polish stringed instruments) and used it to make something that sounds much closer to my target, with a more organic feel.
> What is the use case for music generation models?
New types of electronic instruments.
We’ve been able to use analog circuits, digital logic, and then computers to generate sounds for decades… aka synthesizers.
I would love to see synthesizers which use music generation models under the hood to create new sounds. And / or new interfaces to create different types of instruments.
There’s a lot to explore here, in the same way there was (is) lots of exploration of electronic music starting I suppose with the Theremin in the 1930s.
It's the only way for Spotify to turn a profit without all the human work of having to scout, sign and promote flesh-and-blood artists, the things that real music labels do.
streamers and youtubers are constantly looking for royalty free music options.
i could see something like this baked into an editing tool that allowers video editors to specify a tone or style of music in plain language to serve as background music.
An actual serious answer is to help musicians brainstorm while writing. It's so good at helping me come up with ideas, or converting an idea to another genre.
If the computer is fast enough to keep up with real time music, one could imagine a model that can jam with you with other instruments, reacting to and complementing what you're doing.