Stream speech sentence-by-sentence
Same request body as POST /v1/tts, but the response is delivered as each sentence finishes synthesizing — lower time-to-first-audio on long text. Auth and metering are identical to /v1/tts.
The body is a sequence of frames: a 4-byte big-endian length, followed by that many bytes of one complete WAV. Read a length, read that many bytes (one playable WAV chunk), repeat until the stream closes. The X-Tokay-Stream: wav-frames-v1 header identifies the framing. Most callers should use the SDK’s geko.tts.stream(), which wraps this as an async iterable — see the streaming guide.
Authorizations
Body
Text to synthesize (up to ~5000 characters).
"Сәлеметсіз бе! Тапсырыс нөмірі 152, сомасы 5500 ₸."
Model id.
Voice name from GET /v1/voices. Defaults to the model's default voice.
Speed multiplier.
0.5 <= x <= 2Diffusion steps: 16 fast, 32 quality.
Expand numbers, currency, and dates into spoken Kazakh.
Response
A stream of length-prefixed WAV frames (wav-frames-v1).
The response is of type file.