Adapt
Mini toolsStable Audio 3 Medium
By Stability AI
Stable Audio 3 Medium is the 2B-parameter released model in Stability AI’s Stable Audio 3 family. It is a text-to-audio latent diffusion model for generating both music and sound effects from English prompts, with support for variable-length generation, audio inpainting, and continuation of short recordings. Stability AI describes Stable Audio 3 as using a semantic-acoustic autoencoder plus adversarial post-training to improve speed, fidelity, and prompt adherence, with the small and medium weights released for consumer-grade hardware under the Stability AI Community License.
New
Multimodal
Gen 3
Overview
Stable Audio 3 Medium is Stability AI’s 2B text-to-audio diffusion model for higher-capacity music, sound-effect generation, and audio editing.
About Stability AI
We’ll help you make it like nobody’s business.
No creative challenge too big, no timeline too tight. Get to production with Stability AI, your enterprise-ready creative partner.
Tools using Stable Audio 3 Medium
No tools found for this model yet.
Last updated: May 22, 2026
