Stability AI Unveils Stable Audio 3: Revolutionizing AI Music Creation with New Open-Source Models

Stability AI logo

**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		

	<div>
		<a href="https://www.billboard.com/pro/umg-stability-ai-partnership-develop-music-creation-tools/">

		

AI music generator poster. Robot with guitar near smartphone with mic. Melodies and songs. Artificial Intelligence and Machine Learning. Landing webpage design. Isometric vector illustration

		</a>
</div>

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. 

• 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.