On: Stable-Audio-Demo

[reissbaker]

This is incredibly good compared to SOTA music models (MusicGen, MusicLM). It looks like there's also a product page where you can subscribe to use it, similar to Midjourney: https://www.stableaudio.com/

Sadly it's not open-weight and it doesn't look like there's an API (again like Midjourney): you subscribe monthly to generate audio in their UI, rather than having something developers can integrate or wrap.

[nullandvoid → reissbaker]

I was hoping to use it to generate some sound effects to use in a game I'm working on - but looks like I need an "enterprise license" (https://www.stableaudio.com/pricing)

Why does this have a different clause I wonder, and doesn't just fall under "In commercial products below 100,000 MAU"?

[emadm → nullandvoid]

Different deal with the underlying data holders with revenue share etc

[emadm → reissbaker]

There is a CC licensed version soon plus API.

Models are advancing very fast, will be quite the year for music.

[reissbaker → emadm]

Any chance of a commercially licensed version? CC is alright for research but I feel like the real meat of a lot of these models is finetuning.

(Or, will the API support finetuning?)

[ex3ndr → reissbaker]

Thankfully you can train it at home, the bigger question is a data.