google_meet

Automate Google Meet joining, transcription, and real-time voice interaction via headless browser.

Updated Jul 13, 2026
One-click install
npx skills add https://github.com/zangjeicy/Hermes --skill google-meet-zangjeicy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: google_meet
Source: https://github.com/zangjeicy/Hermes/tree/main/plugins/google_meet
Command: npx skills add https://github.com/zangjeicy/Hermes --skill google-meet-zangjeicy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, websockets, and includes scripts (resource) components.

What problem does it solve?

This skill solves the challenge of manually taking notes during Google Meet calls and the inability of AI agents to participate or respond in real-time during live meetings.

Core Features & Use Cases

  • Live Transcription: Automatically joins meetings and scrapes live captions into a persistent transcript file.
  • Real-time Interaction: Enables the agent to speak directly into the meeting using OpenAI Realtime voice synthesis.
  • Use Case: Use this skill to have an AI agent sit in on your standup meeting, transcribe the discussion, and provide a summary with action items immediately after the call ends.

Quick Start

Use the google_meet skill to join the meeting at the provided URL and start transcribing the conversation.

Frequently Asked Questions about google_meet

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

FAQPage Schema
How do I automate Google Meet transcription and meeting notes?

Google Meet transcription is automated by using headless browser automation to join sessions and scrape live captions into a persistent meeting notes transcript file. This eliminates manual note-taking during remote collaboration.

Can an AI agent participate in real-time voice interaction during Google Meet sessions?

Yes, real-time voice interaction is enabled during Google Meet sessions by routing duplex audio communication through the headless browser. This allows an agent to speak directly into the live meeting using voice synthesis.

Do I need Playwright and websockets to automate Google Meet caption scraping?

Yes, you need Playwright for browser control and websockets for duplex voice communication to automate Google Meet caption scraping. These dependencies enable the headless browser to join meetings and capture live audio.

What is the best way to get action items after a Google Meet standup?

The best way to get action items after a Google Meet standup is deploying an agent to transcribe the discussion and automatically provide a summary with action items immediately after the call ends.

Does this Google Meet automation approach require virtual audio routing?

Yes, this Google Meet automation requires virtual audio routing to facilitate duplex voice communication. This setup allows the agent to simultaneously listen to meeting audio and speak back into the live session.

Are there limitations when using headless browser automation for live meeting transcription?

A limitation of using headless browser automation for live meeting transcription is the strict dependency on browser control environments and virtual audio routing to maintain duplex voice communication without manual intervention.