Stable Audio 2.5
Stable Audio 2.5 remains a documented API option for music generation. The provider's guide recommends describing the genre, instrumentation and mood when requesting a complete composition.
Model design and access
The prompt guide treats the model as a composition tool. It recommends specifying the intended musical result before adding detailed production language. The guide also identifies partner-platform access, which can have separate request formats and service terms.Stable Audio 2.5 official model documentation
The current API accepts stable-audio-2.5 and stable-audio-2 as distinct model values. Both produce 44.1 kHz stereo audio. The 2.5 route remains documented alongside Audio 3.0.Stable Audio 2.0 and 2.5 text-to-audio API
Practical use
Practical guidance. This earlier model can matter when an existing application depends on its musical response. Preserve representative prompts and compare the resulting arrangement before changing models. A prompt guide is not a guarantee of exact notes, lyrics or timing, so review a full track before using it in a finished production.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Maximum duration | Three minutes.Stable Audio 2.5 official model documentation |
| Access | Hosted API; downloadable weights are not published in this guide.Stable Audio 2.5 official model documentation |
Related models
- Stable Audio 2.0
Stability AI · Stable Audio
Stable Audio 2.0 is an earlier hosted generation model with text-to-audio and audio-to-audio workflows.
Launch date not confirmedAPI - Stable Audio 3.0 Large
Stability AI · Stable Audio
A hosted audio-generation model that produces stereo music and sound at 44.1 kHz.
Launch date not confirmedAPI · Provider product