Mini toolsStable Audio 3 Small SFX
By Stability AI
Stable Audio 3 Small SFX is a Stability AI text-to-audio model in the Stable Audio 3 family, specialized for sound effects rather than music. It is a 0.6B-parameter latent diffusion model that generates short or variable-length sound effects from English prompts and supports inpainting for targeted audio editing or continuation. Like the other released Stable Audio 3 small and medium models, it runs through Stability AI’s Stable Audio tooling, uses a transformer-based latent diffusion architecture, and is distributed under the Stability AI Community License with gated Hugging Face access.
New
Multimodal
Gen 3
Overview
Stable Audio 3 Small SFX is Stability AI’s 0.6B text-to-audio diffusion model specialized for fast 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.
Last updated: May 22, 2026
