Voice Agent
Speak into the mic — AssemblyAI transcribes in real-time, then your question is matched against the knowledge base. Matched answers stream pre-recorded audio from S3; unmatched queries fall back to Gemini Live.
Socketdisconnected
Services—
Micidle
Audio—
Session—
Connect and start speaking…
Connect and speak to see timing…
Total (speech → done)
—
Event Log