Sign in

Synthesize one utterance to a raw audio stream

One-shot text-to-speech. The response body is a raw audio stream in the requested output format; the route and the billed character count come back in headers (Speko-Provider, Speko-Model, Speko-Region, Speko-Usage-Characters) because a byte stream has no place for a JSON envelope.

post/v1/tts/speech

Headers

Idempotency-Keystring required

Required on every POST. The Router persists only the key, a content hash, and the request's execution status — never the content itself. For single-part bodies the content hash covers the raw body bytes exactly as sent; for multipart bodies it covers the decoded part payload bytes only — no part headers, no boundary bytes — concatenated in part order (request, then audio), so per-retry boundary strings never change the hash. Reusing a key with the same hash while the original admission is still live returns request_in_progress (retryable); after dispatch it returns request_already_started with the original request id, because stateless mode cannot replay output; reusing a key with a different hash returns idempotency_conflict. Keys are opaque; the Router imposes no format beyond the length bound, and the normative bound is 256 BYTES — maxLength below counts code points, which JSON Schema cannot avoid, so multi-byte keys hit the byte bound first.

Request body

inputstring required

The text to synthesize.

voicestring

Optional: in auto mode the party that picks the provider picks a default voice for it.

languagestring

Optional language hint. Auto routing ranks candidates on that language's benchmark board and the Router picks a voice curated for it; omitted means English.

Response

The synthesized audio, in the encoding, sample rate, and channel count the request asked for.

Changes

Changed in 1 of the 7 revisions of this API.1