Speech-to-Speech (S2S) endpoint configuration.
Controls which AssemblyAI real-time WebSocket endpoint to connect to and the audio sample rates for input (microphone → STT) and output (TTS → speaker).
Sample rate in Hz for audio sent to STT (microphone capture).
Sample rate in Hz for TTS audio received from the server.
The WebSocket URL of the S2S real-time endpoint.
Speech-to-Speech (S2S) endpoint configuration.
Controls which AssemblyAI real-time WebSocket endpoint to connect to and the audio sample rates for input (microphone → STT) and output (TTS → speaker).