Computational Model Studio · Model release
Stable Audio Open 1.0
Generate short stereo sound effects and instrumental audio from text prompts.
Developer: Stability AI · Last verified:
What it is designed to do
Generate short stereo sound effects and instrumental audio from text prompts.
- Primary contribution
- generation transformation
- Input
- text
- Output
- audio (generated sound effect, short instrumental audio)
Documented uses: Generate short stereo sound effects and instrumental audio from text prompts.
Access and deployment
- Stable Audio Open 1.0 publisher weights — restricted. Publisher repository requires acceptance of its license/access conditions. Artifact documentation Local hardware requirements have not been verified. Stability AI Community License (publisher-stated).
Technical profile and review notes
- Construction
- learned
- Representation
- neural
- Normalized architecture tags
- No normalized architecture tag assigned
- Lifecycle
- active
Inclusion rationale: Publisher-distributed gated weights provide an audio-generation artifact separate from hosted music and speech APIs.
Limitations
- The publisher’s described output is recorded as the exact media form shown; surrounding editing tools or orchestration are not attributed to this model.
- Weight access alone does not establish a measured local deployment profile.
- Repository files require accepting the publisher’s access conditions and license.
- The publisher says it is better at sound effects and field recordings than music, and does not generate realistic vocals.
Sources and related Studio records
Sources
Connections
- In areaComputational Models
- Supports functionGenerate music
- Supports functionGenerate sound effects
- ArtifactStable Audio Open 1.0 publisher weights