Voice calls, capture, and Hey Ponder

Ponder can capture microphone audio (you) and optionally system audio (another speaker on a call). Speech becomes transcript bubbles in the room chat; the agent can turn that stream into graph updates.

Microphone capture and participant voice calls are separate. Turning on the mic transcribes your speech without sharing live audio. To speak with other people in the chat, the chat owner turns on Voice call from the chat Settings menu; everyone in the chat joins. Mic on is unmute. You can remain in the call and listen with your mic off, and moving between canvas rooms does not leave the chat-bound call. Only microphone audio can be shared with participants; system audio continues to feed Ponder's transcription privately.

Voice control uses hot phrases (defaults include the product name):

Phrase	Intent
Hey Ponder	Wake the agent
over / trailing go Ponder	Submit the current voice bubble
Go Ponder	Trigger the agent
Stop Ponder	Cancel a running turn
Never mind Ponder	Cancel a wake without submitting

Typed chat always triggers the agent on send. Voice is a way to build the shared mental model while thinking out loud — not the whole product definition.