The model parameter is ignored; vulavula-live in the example is not a selectable checkpoint.
Access
wss://api.lelapa.ai/v1/realtime. Enterprise-only early beta. Mint secrets at POST /v1/realtime/client_secrets using x-api-key; WebSocket subprotocol uses the ephemeral bearer credential.
Regions
Model-specific processing location not established in reviewed sources.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
The May 2026 privacy notice says client data is not used for model training. Audio and transcripts follow the customer data-processing agreement; processing logs follow a separate retention policy. No universal numerical retention period or zero-retention guarantee is published. Service subprocessors are covered by data-processing agreements. Software rights remain with Lelapa; customers retain rights to outputs.
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.
Lelapa Vulavula API
Not verified
No reviewed model inference-cache contract. Browser cookies, credentials, quota refill and stored transcripts are not native prompt caching.
How it works
Not collected
No reviewed model inference-cache contract. Browser cookies, credentials, quota refill and stored transcripts are not native prompt caching.
Minimum reusable input
Not collected
No reviewed model inference-cache contract. Browser cookies, credentials, quota refill and stored transcripts are not native prompt caching.
Lifetime & refresh
Not collected
No reviewed model inference-cache contract. Browser cookies, credentials, quota refill and stored transcripts are not native prompt caching.
How to enable it
Not collected
No reviewed model inference-cache contract. Browser cookies, credentials, quota refill and stored transcripts are not native prompt caching.
Usage fields
Not collected
No reviewed model inference-cache contract. Browser cookies, credentials, quota refill and stored transcripts are not native prompt caching.
Billing rules
Not collected
No reviewed model inference-cache contract. Browser cookies, credentials, quota refill and stored transcripts are not native prompt caching.
Limits & data boundaries
Not collected
No reviewed model inference-cache contract. Browser cookies, credentials, quota refill and stored transcripts are not native prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 16 Oct 2026
What the measurements say
No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.
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
Managed realtime transcription and translation service. The fixed serving ASR checkpoint and its mapping to named proprietary model cards are not disclosed; this is not asserted to be an additional private foundation model.
