Sign up freeSign in
allmodels.ioDocs
Realtime WebSocket referenceNative streaming STT

Native STT client frames

Reference for the binary audio frames and normalized JSON controls a client sends on the native /v1/stt speech-to-text WebSocket.

The raw document is available at /audio/docs/asyncapi.yaml and from the API at api.allmodels.io/asyncapi.yaml.

Reference for the binary audio frames and normalized JSON controls a client sends on the native /v1/stt speech-to-text WebSocket.

Native streaming STT

Address

/v1/stt

Description

Stream binary audio in and receive normalized, sequenced STT events.

Authorization

http
AuthorizationBearer <token>

AllModels API key supplied as the Authorization Bearer token.

Messages

Native TTS server frames SEND

Reference for the frames AllModels returns on the native /v1/tts WebSocket: session status, binary audio chunks, provider status, and errors.

Native STT server frames SEND

Reference for the events AllModels returns on the native /v1/stt WebSocket: normalized, sequenced transcript events or raw provider frames.