Stable Audio Open Small
A 0.5B-parameter latent diffusion transformer released 14 May 2025 with Arm, generating up to 11 seconds of 44.1 kHz stereo audio from English text prompts on-device.
- Up to
- 11 seconds
- Resolution
- 44.1 kHz stereo
- Weights
- Downloadable
- API
- No
- Commercial use
- Permitted subject to conditions
It is better at sound effects and field recordings than at music and cannot generate realistic vocals. Superseded for most uses by the Stable Audio 3.0 Small models but still the best-documented open Stable Audio release.
Released under the Stability AI Community License.
Revenue threshold: free below $1,000,000 in annual revenue, chargeable above it.
- Free only below a revenue threshold. If you are near or over $1M revenue you need the Enterprise License either way
Specification
- What it takes in
- text
- What it makes
- audio
- Maximum duration
- 11 seconds
- Maximum resolution
- 44.1 kHz stereo
- Controls
- style-prompting
- Weights
- Downloadable
- API
- No
- Pricing
- Free download; governed by the Stability AI Community License.
- Released or updated
- 2025-05-14
Strengths
- Fully auditable CC-licensed training corpus - strongest provenance story in this set
- Only 0.5B parameters, runs on-device
- 44.1 kHz stereo output
- Variable-length generation
Weaknesses
- 11-second hard ceiling
- Cannot generate realistic vocals
- Inconsistent across genres and non-Western musical styles
- English prompts only
- Model card wording on commercial use conflicts with the Community License text
Best for
- Short sound effects, foley and ambience
- Research and fine-tuning where training-data provenance must be defensible
Where the sources disagree
Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.
- The Hugging Face card says commercial use requires separate licensing from stability.ai; the Community License itself grants free commercial use below $1M annual revenue. Resolve in favour of the Community License text but expect Stability to point enterprises at the Enterprise License.
What to understand before using it
Explainers naming the mechanisms this model's own documentation mentions.
MCP servers that front Stability AI
Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.
-
Audio Analyzer
Gives LLMs ears. Spectral, harmonic, rhythm, stereo, and structural audio analysis.
-
Audiolla
Self-hosted MCP server: audio stems, mastering, MIR analysis, DSP, MIDI, speech tools.
-
Civitai
Civitai MCP.
-
Cochlea
Render, analyze, and verify audio (WAV/FLAC/mp3/ogg) offline and deterministically via MCP tools.
-
Comfyui
MCP server + Claude Code plugin for ComfyUI: run workflows, generate images, manage models & VRAM.
-
Corent
Generate images and videos via the Corent API, auto model routing with provider fallback.
See it from the vendor
Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.
Nearby in the directory
Stable Audio 3.0 Large
The flagship closed-weights model in the Stable Audio 3.0 family, released 20 May 2026 and aimed at music platforms and high-volume production. It gen
Music and sound
Stable Audio 3.0 Medium
The open-weights mid-size member of the Stable Audio 3.0 family, released 20 May 2026 for full song composition with tracks up to 6:20. Weights are pu
Music and sound
Stable Audio 3.0 Small and Small SFX
Two open-weight on-device variants released 20 May 2026. Small runs full music composition on a mobile device or consumer laptop with tracks up to two
Music and sound