Stability AI releases a new family of audio models called Stable Audio 3.0 that is trained on licensed data; the top model can generate six-minute songs TechCrunch 2026-05-21 Ivan Mehta Stability AI, Stable Audio 3.0 Related Coverage Stability AI Launches Improved Music Models Billboard · Kristin Robinson Meet Stable Audio 3.0, the model family built for artistic experimentation with open-weight models Stability AI · Louisa Marshall Stability AI launches Stable Audio 3.0 with up to six-minute tracks and open weights The Decoder · Jonathan Kemper Stability AI launches its latest, fully-licensed music model Music Ally · Stuart Dredge Stability AI Launches Stable Audio 3.0 for Developers WinBuzzer · Markus Kasanmascheff Stability AI launches new audio models that can generate 6-minute music tracks Music Business Worldwide · Mandy Dalugdug