google_meet

Join Google Meet sessions to scrape live captions into structured transcripts.

1|Updated Jul 31, 2026
One-click install
npx skills add https://github.com/icyzh/hermes-web --skill google-meet-icyzh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: google_meet
Source: https://github.com/icyzh/hermes-web/tree/main/plugins/google_meet
Command: npx skills add https://github.com/icyzh/hermes-web --skill google-meet-icyzh

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill eliminates the manual burden of note-taking and follow-up tracking during Google Meet calls, ensuring you never miss critical action items or discussion points.

Core Features & Use Cases

  • Live Transcription: Automatically scrapes and logs live captions from Google Meet calls into a structured transcript file.
  • Real-time Interaction: Enables the agent to speak directly into the meeting using OpenAI Realtime voice synthesis.
  • Remote Node Support: Allows the bot to run on a separate machine (like a Mac with a signed-in Chrome profile) while the agent gateway runs on a headless Linux server.

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 note taking?

To automate Google Meet transcription, this Skill joins your session via Playwright browser automation to scrape live captions and log them into a structured transcript file. It eliminates manual note-taking by capturing discussion points and generating follow-up action items.

Can I use Playwright to join Google Meet sessions for real-time voice interaction?

Yes, you can use Playwright to join Google Meet sessions for real-time voice interaction. The Skill supports optional duplex voice communication via OpenAI Realtime voice synthesis, enabling the agent to speak directly into the meeting through a configured audio bridge.

Do I need a remote node architecture to run meeting summarization on a headless Linux server?

You need a remote node architecture to run meeting summarization on a headless Linux server if you require a signed-in Chrome profile. The Skill supports running the bot on a separate machine like a Mac, while the agent gateway operates on the headless server.

What is the best way to generate meeting action items from live captions?

The best way to generate meeting action items from live captions is to use an automated agent that scrapes real-time voice data from Google Meet. This Skill processes the live transcription to produce structured meeting summarization and follow-up action items.

Does Google Meet caption scraping work without an audio bridge configuration?

Google Meet caption scraping works without an audio bridge configuration because it relies on Playwright browser automation to capture text. However, the optional audio bridge is required if you want to enable duplex voice communication and real-time voice interaction.