What problem does it solve? Attending and documenting Google Meet calls manually is time-consuming, and automating meeting participation requires fragile browser automation, caption scraping, and audio routing that most tools don't handle. This Skill lets an AI agent join a Meet call as a bot, capture a live transcript, optionally speak in the call, and produce follow-up summaries and action items. ## Core Features & Use Cases - Automated Meeting Transcription: A headless Chromium bot joins a Meet URL, enables live captions, and scrapes them into a timestamped transcript file via a DOM MutationObserver. - Realtime Voice Participation: In realtime mode, the agent speaks into the call through OpenAI Realtime TTS routed into Chrome's microphone via a PulseAudio null-sink (Linux) or BlackHole (macOS), with best-effort barge-in when humans interrupt. - Remote Node Execution: The bot can run on a separate machine (e.g., a Mac with signed-in Chrome) controlled from a headless Linux gateway over a token-authenticated WebSocket connection. - Use Case: Ask the agent to sit in on your daily standup; it joins the call, records the transcript, and afterwards summarizes the discussion, extracts action items, and sends the recap to your team channel. ## 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.