google_meet

Automate Google Meet call joining, live caption transcription, and follow-up summaries.

Updated May 2, 2026
One-click install
npx skills add https://github.com/AlvaroBiano/hermes-agent --skill google-meet-alvarobiano
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: google_meet
Source: https://github.com/AlvaroBiano/hermes-agent/tree/main/plugins/google_meet
Command: npx skills add https://github.com/AlvaroBiano/hermes-agent --skill google-meet-alvarobiano

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables your Hermes agent to join Google Meet calls, capture live captions into a transcript, and perform follow-up actions such as summarization and note-taking for post-meeting tasks.

Core Features & Use Cases

  • Live transcription: join Meet calls and scrape real-time captions into a searchable transcript.
  • Realtime speaking: optional mode where the agent can speak in the meeting via OpenAI Realtime.
  • Follow-up automation: generate summaries, action items, and notes from transcripts for post-meeting workflows.

Quick Start

Join a Google Meet URL and start transcribing captions with the Hermes agent.

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 for live meeting notes?

Automate Google Meet transcription by deploying a browser automation agent to join calls and scrape real-time captions into a searchable transcript. This captures live spoken dialogue directly from the meeting interface for immediate note-taking.

Can I use an AI assistant to speak during Google Meet calls?

Yes, an optional realtime speaking mode allows an AI assistant to participate and speak during Google Meet calls. This functionality is powered by an OpenAI Realtime bridge integrated directly into the meeting workflow.

Does Google Meet automation work on both Linux and macOS?

Google Meet automation supports both Linux and macOS environments. The agent performs platform checks before initiating Playwright-driven browser automation to join calls and capture live captions across these operating systems.

How do I generate action items and summaries after a Google Meet call?

Generate summaries and action items from Google Meet calls by processing the captured transcript after the meeting ends. The agent performs follow-up automation on the transcribed captions to extract relevant post-meeting notes and tasks.

Can I execute Google Meet joining remotely across different network nodes?

Yes, remote execution across network nodes is supported for joining Google Meet calls. The automation path utilizes a node-based remote deployment with token-based authentication to manage the browser session and transcription capture.

What is the best way to scrape real-time captions from a Google Meet video call?

The best way to scrape real-time captions from Google Meet is using Playwright-driven browser automation. This method programmatically controls the browser session to reliably extract live caption data into a searchable transcript format.