Stability AI releases Stable Audio 3.0 open-weights music model family
Stability AI has released Stable Audio 3.0, a family of open-weights music generation models trained on fully licensed data. The suite includes three downloadable models and an enterprise API tier, offering variable-length generation up to six minutes and commercial-use rights under a community license.
Stability AI has released Stable Audio 3.0, a family of music generation models trained on fully licensed data. The release includes four variants: Small SFX for on-device sound effects, Small for full on-device music composition, Medium supporting tracks up to six minutes and twenty seconds, and Large for high-volume, low-latency enterprise use via API and self-hosting.
Stable Audio 3.0 Small, Small SFX, and Medium are available as open weights on Hugging Face. Under the Stability AI Community License, users own their outputs and may distribute and commercialize them; organizations with more than $1 million in annual revenue require an Enterprise License, which includes legal indemnification and white-glove fine-tuning support.
The new architecture features a semantic-acoustic autoencoder enabling variable-length generation at per-second granularity, LoRA customization, and audio inpainting for segment editing and causal continuation. Stability AI developed the suite in partnership with Universal Music Group and Warner Music Group.
Source: Stability AI
The Wire · Newsletter
One careful email,
every Monday.
The week's most important AI stories, lightly edited and personally vouched for. No autoplay, no spam, easy to leave.
Comments · 0
Sign in to join the discussion.
Be the first to leave a thought.