Target language code required; source optional. Reviewed examples include English, Hausa and Yoruba; complete supported pair inventory not established.Source for Language coverage (opens in a new tab)
Billing account shares 3/5/10/20/40 concurrent calls across TTS, STT, translation and diacritics for Tiers 1–5. Enterprise limits are reviewed. Suggested spend does not automatically upgrade an account. Fixed UTC minute windows; higher tiers do not grant queue priority. Translation input words/minute: 2000, 5000, 10000, 25000, 50000.Source for Request quotas (opens in a new tab)
Published price
$1 per 10,000 words. Quotas count whitespace-delimited input words. Explicit currency code, billing rounding and minimum charges remain unverified.Source for Published price (opens in a new tab)
Access & pricing
Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.
Current route does not publish an immutable model selector. Voice and language choices are not checkpoint IDs.
Access
POST https://api.spitch.app/v1/translate; Bearer authentication. JSON text and target, optional source, tone and formality.
Regions
US processing is described by current privacy text, with service providers in other locations; complete model-specific residency and subprocessors are unverified.
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Current privacy text excludes paid-product personal data from model training, but also contains a broad content-improvement clause. Confirm scope for the exact API plan, including free credits. Retention follows agreements, processing needs and legal obligations; backups may remain. X-Data-Retention: false disables automatic artifact storage according to the changelog; this is not a universal no-logging or zero-retention commitment. Processing in the US and sharing with service providers elsewhere are described.
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.
Spitch API
Not verified
Reusable files and saved audio are not a documented inference-cache contract.
How it works
Not collected
Reusable files and saved audio are not a documented inference-cache contract.
Minimum reusable input
Not collected
Reusable files and saved audio are not a documented inference-cache contract.
Lifetime & refresh
Not collected
Reusable files and saved audio are not a documented inference-cache contract.
How to enable it
Not collected
Reusable files and saved audio are not a documented inference-cache contract.
Usage fields
Not collected
Reusable files and saved audio are not a documented inference-cache contract.
Billing rules
Not collected
Reusable files and saved audio are not a documented inference-cache contract.
Limits & data boundaries
Not collected
Reusable files and saved audio are not a documented inference-cache contract.
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
Commercial managed API with reserved service software rights. The public docs do not identify an immutable private checkpoint or establish the exact backing model license. This record is a managed capability, not a claim that all Spitch weights are closed.
