Stability AI releases a new audio model that can create six-minute songs

Stability AI has launched Stability Audio 3.0, a new family of music generation models.

The lineup includes small models for clips up to two minutes, plus medium and large models that can produce full compositions lasting up to 6 minutes 20 seconds.

Three of the four models are open weights, while the largest is available only through API access, paid self-hosting, and enterprise licensing.

Stability AI says the models were trained on fully licensed data and is also developing tools for professional musicians.