28 system voices plus account-private custom voices. Any voice can speak any supported language; roster headings describe original design language.Source for Voice controls (opens in a new tab)
Reference includes HLS m3u8, absent from the guide/SDK enum. Compressed bitrate: 32k, 48k, 64k, 96k, 128k (default), 192k.
Request limits
Custom voice reference: single speaker, 2–30 seconds, at most 10 MB; transcript at most 2000 characters, name at most 120. Explicit speaker consent required. At most 100 custom voices/account. These are enrollment limits, not synthesis prompt or output limits.Source for Request limits (opens in a new tab)
Request quotas
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. TTS generated seconds/minute: 180, 300, 600, 1200, 2400.Source for Request quotas (opens in a new tab)
Published price
$0.0014 per second of generated audio. Dollar currency code and separate voice-enrollment charges are not established by the reviewed rate page.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/speech; Bearer authentication. JSON text, voice and optional language, format, speed, bitrate and sample_rate. Returns streamed binary audio.
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.
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.
