Stable Audio Open 1.0: Open Source Text-to-Audio Generation by Stability AI

Stable Audio Open 1.0 is Stability AI's open-source text-to-audio model capable of generating ambient music, foley, and sound effects up to 47 seconds.

S

Stable Audio Open 1.0

Text-to-AudioSound EffectsFoleyOpen Source

Open-source text-to-audio model by Stability AI. Generates ambient music, foley, and sound effects up to 47 seconds from natural language prompts. Built on a latent diffusion architecture with a 1.2B parameter U-Net and a text conditioning module.

Hugging FaceGitHubResearch
DeveloperStability AI
Release Date2024-08
Architecture1.2B Latent Diffusion U-Net
LicenseStability-AI-Open-RAIL-M
Max Duration47 seconds
Sample Rate44.1 kHz
CapabilitiesAmbient music, foley, sound effects

Guides and workflows related to this model series.

No articles found.