Stable Audio Open

“The new model was trained on audio data from FreeSound and the Free Music Archive. This allowed us to create an open audio model while respecting creator rights.”

This should be standard: commons go in, commons go out.

Re: Stable Audio Open

#5

Post by mastermedo » Wed, Jun 05, 2024, 5:45 PM UTC

hehdhdjehehegwv wrote: post #4

Highly commendable: “The new model was trained on audio data from FreeSound and the Free Music Archive. This allowed us to create an open audio model while respecting creator rights.” This should be standard: commons go in, commons go out.

Except here the out is not commons if I understand correctly.

EDIT: might be cc, non commercial

Re: Stable Audio Open

#6

Post by simonw » Wed, Jun 05, 2024, 5:46 PM UTC

minimaxir wrote: post #2

Note that this has the typical noncommercial "you have to pay for a membership to use commercially" Stability license.

Sigh:

    Stable Audio Open is an open source text-to-audio model [...]

License: https://huggingface.co/stabilityai/stable-audio-open-1.0/blo...

    STABILITY AI NON-COMMERCIAL RESEARCH COMMUNITY LICENSE AGREEMENT

Stability are one of the worse offenders for abusing the term "open source" at the moment.

Re: Stable Audio Open

#7

Post by samfriedman » Wed, Jun 05, 2024, 5:48 PM UTC

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.

Re: Stable Audio Open

#8

Post by bufferoverflow » Wed, Jun 05, 2024, 5:50 PM UTC

It produces decent audio, but something unpleasant about its high frequencies. And no voices, it doesn't seem to talk or sing.

Udio, so far, is undefeated.

And ElevenLabs' music demos were very very impressive, but it's still not released.

Re: Stable Audio Open

#9

Post by asylteltine » Wed, Jun 05, 2024, 5:53 PM UTC

simonw wrote: post #6

minimaxir wrote: post #2

Note that this has the typical noncommercial "you have to pay for a membership to use commercially" Stability license.

Sigh: Stable Audio Open is an open source text-to-audio model [...] License: https://huggingface.co/stabilityai/stable-audio-open-1.0/blo... STABILITY AI NON-COMMERCIAL RESEARCH COMMUNITY LICENSE AGREEMENT Stability are one of the worse offenders for abusing the term "open source" at the moment.

[dead]

Re: Stable Audio Open

#10

Post by michaelbrave » Wed, Jun 05, 2024, 5:57 PM UTC

samfriedman wrote: post #7

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…

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