Stable Audio 3.0 Small Music
Stable Audio 3.0 Small Music is the music-focused downloadable model in the Small family. It supports text prompts, variable durations and audio editing within the Stable Audio 3 toolchain.
Model design and access
The supplied generation example uses eight sampling steps. The card identifies a pretrained Small Music Base checkpoint beneath this post-trained release. Both use a compressed semantic-acoustic audio representation, while the post-trained version is intended for fast generation.Stable Audio 3.0 Small Music official model documentation
Practical use
Practical guidance. Small Music suits local sketching, interactive music prototypes and offline tools. Two minutes is enough for many cues, but a longer work needs deliberate arrangement or continuation. Review transitions and repeated sections in an audio editor. A lightweight generator does not by itself provide stem separation or precise score control.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | Stable Audio 3.0 Smallstable-audio-3-small-music-base |
| Model size | 433 million parameters in the official model table.Stable Audio 3: official inference repository |
| Maximum sequence | 120 seconds; CPU deployment is supported.Stable Audio 3: official inference repository |
| License | Stability AI Community License; separate terms apply to T5Gemma.Stable Audio 3.0 Small Music official model documentation |
Related models
- Stable Audio 3.0 Medium
Stability AI · Stable Audio
A latent-diffusion model for music and sound generation, editing and continuation.
Launch date not confirmedDownloadable - Stable Audio 3.0 Small SFX
Stability AI · Stable Audio
A compact text-to-audio model for sound effects with downloadable weights.
Launch date not confirmedDownloadable