Identity
- Status
- active
- Developer ID
stabilityai/stable-audio-3-medium- Released
- May 20, 2026
- Version
- stable-audio-3-medium
- License
- other
Stability AIStable Audio 3 Medium
stable-audio-3-medium is an open-weight audio-generation model published by Stability AI.
- Token context
- Unknown
- Inputs
- Text
- Outputs
- Audio
- Released
- May 20, 2026
Providers & Pricing
1 current hosted offerings
No Directly Sourced Provider Price Yet
API pricing is provider-specific and stays unknown until a serving provider publishes an exact offering for this model version.
At a Glance
Model Facts
Capacity
- Token context
- Unknown
- Maximum output
- Unknown
- Total parameters
- 2.3B
- Active parameters
- Unknown
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text
- Outputs
- Audio
- API available
- Yes
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- No
- Vision
- No
- Tool calling
- No
- Capabilities
- generation
This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
Aliasesstabilityai/stable-audio-3-medium, stabilityai/stable-audio-3-medium
Explicit Unknowns
- Maximum output
- Knowledge cutoff
- Provider pricing
Primary Evidence
Sources and Observation Date
stabilityai/stable-audio-3-medium developer model repositoryStability AI · observed Aug 28, 2026stabilityai/stable-audio-3-medium Hugging Face inference-provider mappingHugging Face · observed Aug 28, 2026stabilityai/stable-audio-3-medium README.md at 27b5a21b791bStability AI · observed Aug 28, 2026stabilityai/stable-audio-3-medium immutable Hub API metadataStability AI · observed Aug 28, 2026Introducing Stable Audio 3 and SA-METStability AI · observed Aug 28, 2026Hugging Face catalogHugging Face · observed Sep 2, 2026
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
Stable Audio 3 MediumStability AI | vs |  Lyria 3.5Google DeepMind | cross-developer peersaudio |
Stable Audio 3 MediumStability AI | vs |  MiniMax Music3MiniMax | cross-developer peersaudio |
Questions
Stable Audio 3 Medium FAQs
What is Stable Audio 3 Medium?+
stable-audio-3-medium is an open-weight audio-generation model published by Stability AI. It is developed by Stability AI and its current sourced lifecycle status is active.
What inputs and outputs does Stable Audio 3 Medium support?+
Stable Audio 3 Medium's current record lists Text as input and Audio as output.
Is Stable Audio 3 Medium available through an API?+
Stable Audio 3 Medium is marked as API-available. The directly sourced provider records currently include Hugging Face.
How much does Stable Audio 3 Medium cost through an API?+
No directly sourced token price is currently attached to Stable Audio 3 Medium. Missing prices remain unknown rather than being inferred from another model or provider.
How large is Stable Audio 3 Medium?+
The current record lists 2.3B total parameters and an unknown active parameter count. Its architecture is Latent diffusion transformer.
What capabilities and tasks does Stable Audio 3 Medium support?+
Stable Audio 3 Medium's recorded capabilities are generation. Its supported tasks are audio.
Can Stable Audio 3 Medium be self-hosted?+
Stable Audio 3 Medium is an open-weight model. Self-hosting is supported, and the recorded license is other.
Does Stable Audio 3 Medium have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are stabilityai/stable-audio-3-medium.
Which models can Stable Audio 3 Medium be compared with?+
The current compatible peer set includes Lyria 3.5 and MiniMax Music3. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →
How current is the Model Markets record for Stable Audio 3 Medium?+
Stable Audio 3 Medium was last verified Aug 28, 2026 from Stability AI's primary source, “stabilityai/stable-audio-3-medium developer model repository.” The evidence is classified as official fact.