Stability AI releases a new family of audio models called Stable Audio 3.0 that is trained on licensed data; the top model can generate six-minute songs (Ivan Mehta/TechCrunch)
Get the Tech newsletter
Daily tech — startups, AI labs, chips, the launches that shape the next decade. Free.
- Stability AI released Stable Audio 3.0, a new family of audio generation models.
- Stable Audio 3.0 is trained on licensed data rather than uncurated internet audio.
- The top model in the Stable Audio 3.0 suite can produce songs up to six minutes long.
Why it matters: Music producers and content platforms can now generate longer AI‑crafted tracks without the legal risk of unlicensed audio, potentially cutting production costs and speeding up content pipelines.
