Stableaudio
App in the BluixApps catalog
What it is
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.
What it's for
- Sound effects (foley) — footsteps, weather, ambient sounds
- Short musical phrases — drum loops, melodies, samples
- Soundscape design — atmospheres, environments
- Game sound effects — UI sounds, ambient layers
- Audio assets at scale — generate library of sounds for games/video
- NOT for full songs — use MusicGen for that
Who it's for
- Game developers generating sound effects libraries
- Video editors needing foley for productions
- Sound designers prototyping audio concepts
- App developers generating UI sounds
- Music producers creating sample libraries
- Hosting providers offering audio gen tier
Why teams pick Stable Audio Open over alternatives
- Stability AI Community License — commercial OK up to $1M revenue (then commercial license)
- Sound effect specialization — better than MusicGen for foley/SFX
- 44.1 kHz stereo — production-grade audio quality
- 47 seconds max — longer than most open audio models
- Active Stability AI development — frequent improvements
- Trained on permissive data — fewer copyright concerns vs music-trained models
Integrations
- Gradio web UI out of box
- stable-audio-tools Python library for batch
- HuggingFace gated download — accept license + HF_TOKEN required
- Pair with video AI: SFX for generated video B-roll
- Pair with MusicGen: SFX for atmosphere + MusicGen for melodies
Notable users & community
- 3k+ GitHub stars
- Stability AI corporate backing
- Used in indie game production pipelines
- Active community fine-tunes for specific sound categories
- Featured in audio AI roundups
Tips & operations
- HF authorization required: accept license at https://huggingface.co/stabilityai/stable-audio-open-1.0
- VRAM: 8 GB GPU recommended for 8-step inference
- Length: 1-47 seconds (longer = more memory)
- CFG scale: ~7 default; higher for stronger prompt adherence
- Sample prompts:
- "Rain on a wooden roof, distant thunder, soft wind"
- "808 trap beat, dark, slow tempo, 70 BPM, with hi-hats"
- "Ocean waves crashing on rocks, seagulls, peaceful morning"
- Output: stereo WAV at 44.1 kHz
- License check: Stability AI Community License — review for commercial use
What we ship in BluixApps
- Cloned
Stability-AI/stable-audio-toolsrepo - pytorch/pytorch CUDA 12.4 base + ffmpeg + libsndfile1
- run_gradio.py launcher with
--model-config stabilityai/stable-audio-open-1.0 - Persistent volumes: repo, models (~6 GB), output
- Port 7869 mapped
- Install report at
/root/bluixapps/stableaudio.txt - HF license + token requirement clearly noted
- Sample prompt library in install report
- GPU pre-flight check via
bluixapps_ensure_nvidia_runtime - Backup hook covers models + outputs
Get this app — pick a BluixApps plan
Same catalog. Scaling tenant isolation, white-label and support tier.
| Tier | Tenants | Catalog | Support | White-label | Monthly | |
|---|---|---|---|---|---|---|
| Stacks | 1 | 19 curated stacks | Standard | — | $19/mo | DetailDeploy |
| Starter | 10 | Full catalog | Standard | +$15–25/mo | $49/mo | DetailDeploy |
| Pro | 25 | Full catalog | Priority bugfix | +$15–25/mo | $149/mo | DetailDeploy |
| Growth | 100 | Full catalog | Priority bugfix | +$15–25/mo | $349/mo | DetailDeploy |
| Scale | 500 | Full catalog | 7-day window | +$15–25/mo | $799/mo | DetailDeploy |
| Enterprise | Unlimited | Full catalog | Priority 7-day | Bundled | $1,499/mo | DetailDeploy |
