Descriptive catalog identity, not a verified selectable API ID.
Access
Paper and examples available. No original public checkpoint or callable inference contract verified.
Regions
Research deployment only; public availability and residency are not established
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
The cited research release does not supply a current production processing/retention agreement. Research access or an expired demonstration is not a production API entitlement.
Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.
01 / INITIAL INPUTProcess & retain
The system processes eligible input and retains reusable state.
02 / LATER REQUESTCheck available state
Reuse depends on matching input, session state and the cache policy.
03 / CACHE HITReuse & generate
Reusing state can reduce repeated work. Any charges follow the billing rules below.
Meta · research reference
Not verified
No published service cache policy for this research record.
How it works
Not collected
No published service cache policy for this research record.
Minimum reusable input
Not collected
No published service cache policy for this research record.
Lifetime & refresh
Not collected
No published service cache policy for this research record.
How to enable it
Not collected
No published service cache policy for this research record.
Usage fields
Not collected
No published service cache policy for this research record.
Billing rules
Not collected
No published service cache policy for this research record.
Limits & data boundaries
Not collected
No published service cache policy for this research record.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
What the measurements say
AudioCaps text-to-audio FAD
Meta research authors · provider-reported
0.77FAD
Table 5 Sound-model result. Generation selects the best CLAP match among 32 samples per prompt; not a single-sample quality claim or unified Audiobox score. Lower is better.
Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.
The record behind the model
Why it is included
Meta describes limited, hand-selected researcher access under a research-only license rather than public weights. The original trained research model is distinct from open AudioCraft, MusicGen and Audiobox Aesthetics. The public demo has been discontinued; the paper remains a research reference.