Stable Audio Open 1.0

model·generative audio model·active

Open-weight latent-diffusion model for short text-to-audio generation.

Recorded facts

Official site	https://huggingface.co/stabilityai/stable-audio-open-1.0 ↗
Geography	unknown
huggingface repo	stabilityai/stable-audio-open-1.0
api	unknown
inputs	text
license	Stability AI Community License
outputs	audio
weights	public
modalities	audio; text
dependencies	unknown
model family	Stable Audio Open
access method	downloadable weights; Diffusers; Stable Audio Tools
exact version	1.0
repository links	https://huggingface.co/stabilityai/stable-audio-open-1.0
evaluation results	unknown
evidence separation	developer claims: · measured results: · independent evaluations:
developer maintainer	Stability AI
material us relevance	Publicly accessible in or materially offered to the United States market as of snapshot.
documented capabilities	short sound-effect and production-element generation; variable duration up to 47 seconds
products exposing model	unknown
commercial use conditions	Free commercial use below the license's $1M annual-revenue threshold; Enterprise license otherwise.
known geographic or policy restrictions	Not optimized for full songs, melodies or vocals
safety watermarking disclosure provenance	The research paper reports Audible Magic matching to remove identified copyrighted music from the training corpus.