google_meet

Joins Google Meet calls with a Playwright bot to transcribe captions and speak via OpenAI Realtime.

Updated Aug 22, 2026
One-click install
npx skills add https://github.com/vivekgoquest/hermes-agent-stable --skill google-meet-vivekgoquest
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: google_meet
Source: https://github.com/vivekgoquest/hermes-agent-stable/tree/main/plugins/google_meet
Command: npx skills add https://github.com/vivekgoquest/hermes-agent-stable --skill google-meet-vivekgoquest

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, websockets.

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 that most teams never build. ## 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. - Realtime Voice Participation: In realtime mode, the agent speaks into the call through OpenAI Realtime TTS routed via a PulseAudio null-sink (Linux) or BlackHole (macOS) virtual audio device. - Remote Node Hosting: Run the bot on a separate machine (e.g., a Mac with signed-in Chrome) while the gateway runs on a headless Linux server, connected over authenticated WebSocket. - Use Case: Ask the agent to sit in on your standup, take notes, then summarize the transcript and send follow-up messages or file action items after the call ends. ## Quick Start Ask the agent to join your Google Meet link and take notes on the meeting, then summarize the transcript when it ends.

Frequently Asked Questions about google_meet

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I make a bot join a Google Meet call and transcribe it?▼

Call meet_join with a meet.google.com URL and the bot launches a headless Chromium via Playwright, enables live captions, and scrapes them into a transcript file. Poll progress with meet_status and read captions with meet_transcript.

How can an AI agent speak in a Google Meet call?▼

Join with mode='realtime', which connects an OpenAI Realtime session and routes generated speech into Chrome's fake microphone through a PulseAudio null-sink on Linux or BlackHole on macOS. Then call meet_say with the text to speak.

Does the Google Meet bot work on Windows?▼

No, Windows is not supported. The plugin only registers on Linux and macOS because the realtime audio bridging path is untested on Windows and guest-join Chromium is flakier there.

Why is my Meet bot stuck in the lobby?▼

Guest-mode joins wait in the lobby until a host admits them, and the bot leaves after a 5-minute lobby timeout by default. Running hermes meet auth to save a signed-in Google session skips the guest admission wait.

Can the Meet bot run on a different machine than the agent?▼

Yes, run hermes meet node run on the machine with signed-in Chrome, then approve it on the gateway with hermes meet node approve using the printed bearer token. Pass node='<name>' to any meet tool to operate the remote bot.

What are the limitations of Google Meet caption transcription?▼

Transcripts are only as accurate as Google Meet's built-in live captions, which are English-biased and lossy on overlapping speakers. The bot also supports only one active meeting per install per location.