Stability AI Launches 6-Minute Song Generator

Stability AI has released Stable Audio 3.0, a new family of four audio models capable of generating professional-grade music up to six minutes and 20 seconds long. This more than doubles the output of its 2024 predecessor, with three models available as open weights and the largest accessible only via API or paid self-hosting. The models are built on fully licensed data, backed by deals with Warner Music Group and Universal Music Group. Stability AI is also developing tools for professional musicians, hiring former Universal Audio executive Ethan Kaplan to lead that effort.