What problem does it solve? Attending and documenting Google Meet calls manually is time-consuming, and automating a bot that can both listen and speak in a call requires complex browser automation, caption scraping, and audio routing. This Skill lets an agent join a Meet URL, capture a live transcript, optionally speak in the call, and handle follow-up work like summaries and action items. ## Core Features & Use Cases - Transcribe Mode: A headless Chromium bot joins the meeting, enables live captions, and scrapes them into a timestamped transcript file via a DOM MutationObserver. - Realtime Voice Mode: The bot speaks into the call using OpenAI Realtime, streaming generated PCM audio through a PulseAudio null-sink (Linux) or BlackHole device (macOS) into Chrome's fake microphone, with best-effort barge-in when humans interrupt. - Remote Node Hosts: Run the bot on a different machine than the gateway (e.g., a Mac with a signed-in Chrome) over a token-authenticated WebSocket connection. - Use Case: Ask the agent to sit in on your standup at a Meet URL; it joins as a guest, records the transcript, speaks status updates when prompted, then summarizes the meeting and sends follow-ups after leaving. ## Quick Start Ask the agent to join your Google Meet link and take notes, for example: "join my Meet at https://meet.google.com/abc-defg-hij and summarize it afterwards."