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
Conversation
Connect and start speaking…
Latency
Connect and speak to see timing…
Total (speech → done)
Event Log