Stability AI: New Audio Model Creates 6-Minute Songs

Stability AI has released a new family of audio models called Stability Audio 3.0. The top model can generate professional-grade music over six minutes long. What's interesting is that the medium and large models can create compositions up to 6 minutes and 20 seconds. This is more than double the length of previous versions. Stability AI is making some of these models openly available for use and modification. The largest model is accessible through an API and paid services. The company states its latest audio models are built on fully licensed data, following deals with major music groups. Stability AI is also developing new tools for professional musicians and has hired a former chief digital officer from Universal Audio and Fender to lead this effort. This shows a growing trend of AI companies hiring music executives to bolster their offerings.