Stability AI releases a new audio model that can create six-minute songs
TechCrunch
Stability AI has launched Stable Audio 3.0, a new model family capable of generating high-quality musical compositions up to six minutes long.Summary
Stability AI has unveiled Stable Audio 3.0, a suite of new audio generation models including small, medium, and large versions. The most advanced models can produce professional-grade music lasting over six minutes, doubling the length capabilities of previous versions while maintaining structural and melodic consistency. Stability AI emphasizes that these models are built on fully licensed data, following partnerships with major labels like Warner Music Group and Universal Music Group. While smaller models are being released with open weights, the largest model is restricted to API and paid services, with enterprise licensing required for larger companies.
(Source：TechCrunch)