Meet Stable Audio 3.0, the model family built for artistic experimentation with open-weight models

Stability AI has launched Stable Audio 3.0, a fully licensed family of open-weight music and audio generation models.

Small SFX, Small, and Medium are available as open weights, while the Large model is offered through an API.

The release adds longer variable-length generation, on-device full-track creation, LoRA fine-tuning, and audio inpainting.

Users own the outputs, and commercial use is supported.

The move expands legally usable generative audio tools and could make AI music more practical for creators and businesses.