Sound effects (foley)
footsteps, weather, ambient sounds
// official site: stability.ai ↗
Stable Audio Open is Stability AI's open-weight text-to-audio model — generates 47-second clips of stereo audio at 44.1 kHz from text prompts. Specialized for sound effects, foley, and short musical samples (NOT full songs). High quality + permissive license make it the canonical open audio gen choice.
Stable Audio Open is Stability AI's open-weight text-to-audio model — generates 47-second clips of stereo audio at 44.1 kHz from text prompts. Specialized for sound effects, foley, and short musical samples (NOT full songs). High quality + permissive license make it the canonical open audio gen choice.
The audio equivalent of "Stable Diffusion for sound" — Stability AI's audio offering.
Concrete scenarios where teams pick Stable Audio Open over the SaaS alternative.
footsteps, weather, ambient sounds
drum loops, melodies, samples
atmospheres, environments
UI sounds, ambient layers
generate library of sounds for games/video
use MusicGen for that
If your team profile matches one of these, Stable Audio Open is a strong fit out of the box.
generating sound effects libraries
needing foley for productions
prototyping audio concepts
generating UI sounds
creating sample libraries
offering audio gen tier
When evaluating self-hosted options for this category, here are the dimensions on which Stable Audio Open consistently lands above the alternatives.
The stack you'll plug Stable Audio Open into — services, protocols, and adjacent apps in the BluixApps catalog.
Stability-AI/stable-audio-tools repo--model-config stabilityai/stable-audio-open-1.0/root/bluixapps/stableaudio.txtbluixapps_ensure_nvidia_runtimeOperational guidance from running this in production — what to lock down, what surprises people.