It looks like you're new here. If you want to get involved, click one of these buttons!
Subscribe to our Patreon, and get image uploads with no ads on the site!
Base theme by DesignModo & ported to Powered by Vanilla by Chris Ireland, modified by the "theFB" team.
Comments
https://www.instagram.com/there_i_ruined_it/
At the moment I'm looking for:
* Hamer Watson, SS2, Vintage S, T62.
* Music Man Luke 1, Luke II
Please drop me a message.
I'd guess that most of them are guitarists who've had to deal with trying to record singers at some point in their lives...
The other 1% will be for demo guide tracks to be given to actual session musicians to explain what the composer wants.
EDIT: And if you're a session singer who's not capable of doing better than an AI part written by somebody who's not a singer, then should you actually be doing that job anyway? It's no different to drum plugins in that regard, and - last I checked - there weren't any drummers out of work because of those.
I've attempted to use it several times.
Results vary from
Quite good
Very poor
Didn't work at all and generated 4 empty tracks.
Just wondering if anyone has had better results than me.
Overall as a sketch book idea it's fine and works quickly and well. My question is how soon before people get used to it and it starts becoming the norm?
Whether or not it's a good thing is entirely in the eyes of the beholder.
In the "worst case", it'll enhance the business model for places that just chuck out music as a commodity, but it kinda feels to me like that won't make any difference because that music is just on in the background for most people who listen to it anyway, rather than being actively listened to.
For what it's worth, I spent the weekend building a ChatGPT-alike on my server from the available open source LLMs - it works faster than ChatGPT at comparable quality (for the stuff I'm doing), using a £300 graphics card and a PC from 4-5 years ago.