Provider estimate, not an end-to-end latency guarantee for every language pair.
Generation controls
One source and one target per session; two sessions for bidirectional calls. Optional domain vocabulary, translation dictionary, transcripts and background voice cancellation.Source for Generation controls (opens in a new tab)
Listed for translation backend support; exact model IDs and per-request routing are not disclosed here. AWS provides infrastructure and Daily.co audio streaming.
Listed for translation backend support; exact model IDs and per-request routing are not disclosed here. AWS provides infrastructure and Daily.co audio streaming.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Voice Translation uses Krisp and licensed third-party models. API terms state that content is processed transiently, without content retention or training; limited billing/security/operational metadata remains. This is a cloud service, not the on-device SDK privacy contract.
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.
Krisp Voice Translation API
Not verified
Loading model weights once or reusing an audio session is not a documented discounted prompt-cache feature.
How it works
Not collected
Loading model weights once or reusing an audio session is not a documented discounted prompt-cache feature.
Minimum reusable input
Not collected
Loading model weights once or reusing an audio session is not a documented discounted prompt-cache feature.
Lifetime & refresh
Not collected
Loading model weights once or reusing an audio session is not a documented discounted prompt-cache feature.
How to enable it
Not collected
Loading model weights once or reusing an audio session is not a documented discounted prompt-cache feature.
Usage fields
Not collected
Loading model weights once or reusing an audio session is not a documented discounted prompt-cache feature.
Billing rules
Not collected
Loading model weights once or reusing an audio session is not a documented discounted prompt-cache feature.
Limits & data boundaries
Not collected
Loading model weights once or reusing an audio session is not a documented discounted prompt-cache feature.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
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
The API terms identify proprietary Krisp models combined with licensed third-party models and reserve model weights/parameters. This record is a managed closed service pipeline, not a claim that Krisp created every component or has one end-to-end checkpoint.
