Powered by Smartsupp

Stability AI Debuts Stable Audio 3.0: Generates Professional-Grade Music Over Six Minutes Long



By admin | May 20, 2026 | 3 min read


Stability AI Debuts Stable Audio 3.0: Generates Professional-Grade Music Over Six Minutes Long

Stability AI, the creator of Stable Diffusion, has unveiled a new line of audio models under the name Stability Audio 3.0. According to the company, the flagship model is capable of generating professional-grade music that lasts over six minutes. The release includes four distinct models: small SFX (459 million parameters), small (459 million parameters), medium (1.4 billion parameters), and large (2.7 billion parameters). The two small models are designed for on-device sound and music generation, supporting clips of up to two minutes. In contrast, the medium and large models can produce complete compositions spanning six minutes and 20 seconds, while preserving musical structure and melodic tone. This represents more than double the duration that Stable Audio 2.0, which launched in 2024, could achieve. Stability AI is making the small SFX, small, and medium models available under open weights, allowing anyone to use and modify them. In 2024, the company released Stable Audio Open, which supported music generation of up to 47 seconds. This new family of models marks a significant advancement over those earlier open versions.

Image Credits: Stability AIImage Credits:Stability AI

The large model is exclusively accessible through the company's API and paid self-hosting services. Additionally, businesses with annual revenues exceeding $1 million must obtain an enterprise license. Many tech companies, such as Google and ElevenLabs, are releasing their own models and tools for music generation. However, as ongoing legal battles involving Suno and Udio have shown, licensing data and forming partnerships with music labels may become essential for the long-term viability of these services. Last year, Stability AI secured agreements with Warner Music Group and Universal Music Group to develop models and music creation tools. The company asserts that its latest audio models are built on fully licensed data. The AI startup is also developing a new suite of products aimed at professional musicians, though it has not disclosed specific features. Ethan Kaplan, formerly the chief digital officer at Universal Audio and Fender, is joining the company to lead Stability's professional music offerings. Several AI firms are attempting to strengthen their credibility by hiring music industry executives. Earlier this year, Suno brought on former Merlin CEO Jeremy Sirota as its chief commercial officer, while ElevenLabs hired Derek Cournoyer from indie music publisher Kobalt to serve as strategy lead for its music business.




RELATED AI TOOLS CATEGORIES AND TAGS

Comments

Please log in to leave a comment.

No comments yet. Be the first to comment!