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

Native STT server frames

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

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

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

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 STT client frames RECEIVE

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

Stream-input TTS client frames RECEIVE

Reference for the ElevenLabs stream-input frames a client sends to stream text into TTS on AllModels: init, text chunks, flush, and close.