google_meet

Join Google Meet sessions to scrape live captions into transcripts.

Updated May 4, 2026
One-click install
npx skills add https://github.com/InverterNetwork/hermes-agent --skill google-meet-inverternetwork
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: google_meet
Source: https://github.com/InverterNetwork/hermes-agent/tree/main/plugins/google_meet
Command: npx skills add https://github.com/InverterNetwork/hermes-agent --skill google-meet-inverternetwork

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill solves the problem of manual meeting documentation and the inability of AI agents to participate in live video calls, ensuring no action items or insights are lost.

Core Features & Use Cases

  • Live Transcription: Automatically joins Google Meet calls and scrapes live captions into a persistent transcript file.
  • Real-time Interaction: Supports duplex audio, allowing the agent to speak in meetings via OpenAI Realtime.
  • Remote Node Support: Enables the agent to run the bot on a separate machine (e.g., a user's Mac) while the gateway remains on a headless server.
  • Use Case: A user can instruct the agent to join a standup meeting, take notes, and provide a summary, or even have the agent speak up to provide a status update during the call.

Quick Start

Use the google_meet skill to join the meeting at the provided URL and start taking notes.

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?

Automate Google Meet transcription by using a browser automation tool to join calls and scrape live captions into a persistent transcript file. This enables automated meeting documentation and ensures no action items are lost.

Can an AI agent participate in live video conferences with real-time voice interaction?

Yes, an AI agent can participate in live video conferences with real-time voice interaction by using duplex audio bridging. This allows the agent to speak directly in meetings via OpenAI Realtime to provide updates or status reports.

How does live caption scraping work for remote meeting documentation?

Live caption scraping for remote meeting documentation works by using Playwright to automate a browser that joins Google Meet sessions. It extracts real-time caption data and saves it directly to a persistent transcript file for later summarization.

Do I need Playwright to run an automated meeting bot on a remote node?

Yes, you need Playwright for browser automation to run an automated meeting bot. The bot can run on a separate remote node, such as a Mac, while the gateway remains on a headless server to facilitate agent-led participation.

What is the best way to summarize Google Meet sessions automatically?

The best way to summarize Google Meet sessions automatically is to deploy an agent that joins the call, captures the live transcript via caption scraping, and generates a meeting summary from the persistent transcript file.

Are there limitations to automated meeting documentation via live caption scraping?

Automated meeting documentation via live caption scraping is limited by the availability of live captions in the meeting session. Additionally, real-time voice interaction requires optional audio bridging for duplex voice capabilities.