Brief

Stability AI has launched its new audio generation models, Stability Audio 3.0, capable of producing professional-grade music up to six minutes long. Four models are available, with smaller versions offering open weights for general use and longer compositions. The company has also secured licensing deals with major music labels, ensuring the models are trained on fully licensed data. AI

Stability AI has launched Stable Audio 3.0, a family of open-weight models designed for creative audio generation and experimentation. These models are trained on licensed data, allowing users to own and commercialize their outputs under specific licenses. Key advancements include variable-length generation up to six minutes and the capability for full song composition on portable devices. AI

Stability AI has released its Stable Audio 3 family of models, including small and medium versions, designed for efficient variable-length audio generation and editing. These latent diffusion models operate on a novel semantic-acoustic autoencoder and utilize adversarial post-training to enhance speed and quality. Trained on licensed and Creative Commons data, the models can produce music and sounds in seconds, with the small and medium versions capable of running on consumer hardware. AI