News for hackers. Stuff that matters.
Re:Stable Audio Open by bufferoverflow on Wednesday June 05, 2024 @01:50PM (#40588063)
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 by genericacct on Wednesday June 05, 2024 @02:52PM (#40588822)
Have you tried suno? It is quite good at least for some genres
Re:Stable Audio Open by bufferoverflow on Wednesday June 05, 2024 @06:13PM (#40591205)
Suno is good at generating music, but its voices sound metallic with a dash of high-frequency noise. Which ruins it for me. It's almost there though, I think they will fix it in the next version.
Re:Stable Audio Open by jononor on Wednesday June 05, 2024 @07:13PM (#40591723)
I suspect we will get ML based "upsamplers" / enchancers / artifact removers, similar as we already have for images. That can be used to automatically post process. If they do not already exist?
Re:Stable Audio Open by hierophantical on Wednesday June 05, 2024 @05:35PM (#40590909)
None of these are impressive in the least. Anything I have heard from Udio is basically trash. It is the AI art equivalent of synthetic cats and pretty face shots. Who cares.

What is ultimately going to be undefeated is training your own model.

Re:Stable Audio Open by acureau on Friday June 07, 2024 @04:20PM (#40612568)
I just don't see how any of these examples from Udio or ElevenLabs could be considered good. To me they sound just bland enough that I may be fooled by them if I weren't paying close attention. If I do pay attention it sounds like a song accidentally came about. It sounds like music might in a dream. Eerie.
Re:Stable Audio Open by bufferoverflow on Monday June 10, 2024 @03:12AM (#40631013)
I think if I gave you 20 pieces of music, half of them made by AI, you wouldn't be able to tell which ones are made by AI much better than guessing randomly.
Re:Stable Audio Open by acureau on Tuesday June 11, 2024 @11:55PM (#40654309)
I am certain I could, in fact I'd bet a lot on it. I'd have a hard time distinguishing AI generated images at this point, but earlier on there were major indicators. This tech is still primitive. The lyrics are dead giveaways, the tracks all sound blended together. A 5 second snippet of a song seems coherent, but the songs never go anywhere. If you listen to a lot of music, and have a decent pair of headphones, it's immediately obvious. Someone who makes music would be able to identify the specific flaws better than me.
Re:Stable Audio Open by MrNeon on Wednesday June 05, 2024 @07:03PM (#40591647)
> What is ultimately going to be undefeated is training your own model.

From scratch?

Re:Stable Audio Open by wavemode on Thursday June 06, 2024 @06:18PM (#40603002)
As far as I understand, this isn't competing with Udio? It seems to be designed for creating sound effects and loops, not entire songs.