Skip to main content
  1. Inbound audio streams from the telephony provider over WebSocket.
  2. The transcriber converts audio to text in near real time.
  3. The LLM receives the transcript plus conversation history and generates a response, optionally calling tools.
  4. The synthesizer converts the response to audio, streamed back to the caller.
Each hop adds latency — see Latency for how to minimize it.