AI firm Stability AI has launched its latest audio-generation model, Stable Audio 2.5, which it says is focused on “enterprise-grade sound production”. That means brands and businesses, who the company hopes will turn to AI for “a growing volume of channels, from ads to the in-store experience”.
The new model can create three-minute long tracks “within seconds” with Stability AI saying it’s better than previous versions at musical structure: intros, outros and more. Users can also upload their own audio to use as the seed for generation. Which, yes, will flash a big ‘ALERT’ sign to music rightsholders worried that every brand and their aunt will start uploading Taylor Swift or Drake music to use as the base for their corporate tracks.
However, Stability AI’s blog post announcing Stable Audio 2.5 stressed that “our Terms of Service require that uploads be free of copyrighted material, and we use advanced content recognition to maintain compliance and prevent infringement”.
‘ The preceding article may include information circulated by third parties ’
‘ Some details of this article were extracted from the following source musically.com ’
