Stable Audio 3.0 Small SFX
Stable Audio 3.0 Small SFX is the sound-effects member of the Small family. Its official example generates a short environmental sound from a text description. Downloadable weights support local use and adaptation.
Model design and access
The model uses the same variable-length diffusion and inpainting approach as the wider Audio 3 family. Its card provides an eight-step generation example and links the pretrained Small SFX Base checkpoint. The SFX and Music releases serve different sound-generation roles.Stable Audio 3.0 Small SFX official model documentation
Practical use
Practical guidance. Use precise descriptions of the source, action and recording conditions for effects. Generate separate events when timing must match animation, then place them on the timeline. Review the start and decay of each result. A two-minute allowance is useful for ambience, but it is not a reason to make every effect long.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | stable-audio-3-small-sfx-base |
| Model size | 433 million parameters in the official model table.Stable Audio 3: official inference repository |
| Maximum sequence | 120 seconds; uses the SAME-Small autoencoder.Stable Audio 3: official inference repository |
| License | Stability AI Community License; separate Gemma terms cover T5Gemma.Stable Audio 3.0 Small SFX official model documentation |
Related models
- Stable Audio 3.0 Small Music
Stability AI · Stable Audio
A compact music-generation model that supports text prompts and audio editing.
Launch date not confirmedDownloadable - Stable Audio Open Small
Stability AI · Stable Audio
Stable Audio Open Small is an earlier compact text-to-audio model for short clips.
Launch date not confirmedDownloadable