Stability AI releases Stability Audio 3.0 with models capable of generating six-minute songs

Stability AI released four new audio models under the Stability Audio 3.0 name: small SFX (459M parameters), small (459M parameters), medium (1.4B parameters), and large (2.7B parameters). The medium and large models can create compositions of 6 minutes 20 seconds long while maintaining musical structure and melodic tone, more than double the length of Stable Audio 2.0 released in 2024.

The small SFX, small, and medium models are available with open weights for anyone to use and modify. The large model is available only through API and self-hosting paid services; companies with more than $1 million in revenue would need an enterprise license.

Stability AI built the latest audio models on fully licensed data, following deals with Warner Music Group and Universal Music Group inked last year. Ethan Kaplan, former chief digital officer at Universal Audio and Fender, is joining the company to lead its professional music offering.