Stable Audio 3.0: Stability AI Releases New, Customizable Music Models

Stability AI has announced the launch of Stable Audio 3 — a family of three new AI music models and one audio-based special effects model. Most of these new releases are “open weight,” a term used to describe models that are publicly available and can be downloaded and built on for further development, and are created via licensed training data.

Related

UMG Partners With Stability AI to Develop Music Creation Tools for Artists, Producers

J-Pop Festival Zipangu & Xbox Team Up for Sung Kang Fashion Collab

Kodak Black Arrested for Second Time in Less Than a Month, This Time for Fleeing Law Enforcement

According to the research paper released alongside these four models, they are trained on a combination of licensed audio from production library AudioSparx (806,284 audios) and Creative Commons recordings from Freesound. To ensure no authorized copyrighted material ended up in the dataset from the Creative Commons portion of the data, music recordings were filtered using a tagging tool.

Key improvements from Stable Audio 2.0 to the new releases include variable length generations, allowing for up to six minutes of song to be created, and full song composition on portable devices like phones and tablets.

The roll out includes the following new models:

- Small SFX: This can create sound effects on any device, including on mobile phones and consumer-grade laptops.

- Small: This can make solid musical compositions on all devices but cannot generate over two minutes of song.

- Medium: This model boasts higher musicality (i.e. structure, melodic coherence, and phrasing) and longer track length. Now, the model can create up to six minutes and 20 seconds of song.

- Large: The most advanced model, designed for music platforms and creative applications that need low-latency generation at a high volume.

According to a press release about the new suite of audio models, this is designed to be “setting the stage for what’s next,” which will include “a suite of new products for musicians” that they are currently working on.

News of Stable Audio 3.0’s launch comes after announcements in late 2025 that Stability AI would be partnering with Universal Music Group and Warner Music Group to develop “next generation professional music creation tools” together, as stated in the UMG partnership deal specifically. Based on the details of Stable Audio 3.0 research paper, provided to Billboard , neither of these major music companies are currently part of the Stable Audio training dataset.

_Originally reported by [Billboard](https://www.billboard.com/pro/stability-ai-improves-music-models/)._