Stable Audio

Stable Audio is Stability AI's generative-audio platform for creating music and sound using artificial intelligence. Users can describe desired instruments, genres, moods, arrangements and sound characteristics through natural-language prompts, while supported models can also transform existing audio into new compositions. Stable Audio 2.5 supports text-to-audio, audio-to-audio and audio inpainting, while the newer Stable Audio 3.0 family supports longer, more coherent audio generation and is available through Stability AI's API, enterprise deployment and selected open-weight models. The models were trained using licensed data, and Stability AI provides deployment options ranging from managed cloud APIs to self-hosted models.