Stability AI has launched Stability Audio 3.0, a family of four audio models capable of generating professional-grade music up to 6 minutes and 20 seconds long, more than double the length of its predecessor. The company is releasing three smaller models with open weights while keeping the largest model (2.7B parameters) available only through paid services. This release comes amid growing competition in AI music generation and follows Stability AI's partnerships with major music labels like Warner Music Group and Universal Music Group.
Background
Stability AI is known for developing Stable Diffusion, a popular open-source image generation model. The company has been expanding into audio generation, with previous releases including Stable Audio 2.0 in 2024 which could generate up to 47 seconds of audio.
- Source
- TechCrunch
- Published
- May 20, 2026 at 11:00 PM
- Score
- 7.0 / 10