v1

latestOpenAPI 3.1.02026-07-22247.2 KB
speech

create a streaming session

mint a one-shot WebSocket session for real-time streaming synthesis. returns a ws_url and a token. connect to ws_url?token=<token>, send a JSON synthesis frame, then receive raw PCM int16 little-endian @ 24 kHz mono binary frames followed by a terminal {"type":"done"} JSON frame.

post/v1/tts/ws-connect

Request body

model'muga' | 'mulberry'

which model to use.

textstring required

text to synthesize. sent again in the WebSocket synthesis frame.

Response

a one-shot WebSocket session.

ws_urlstring uri

WebSocket URL to connect to.

tokenstring

one-shot token. pass as ?token=<token> when connecting.

Example response

{
  "ws_url": "wss://silk-api.rumik.ai/v1/tts/ws/abc123"
}
All 2 operations