google_meet

Join Google Meet calls and convert live captions into transcripts.

Updated Apr 9, 2026
One-click install
npx skills add https://github.com/MarbleSodas/Mavis --skill google-meet-marblesodas
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: google_meet
Source: https://github.com/MarbleSodas/Mavis/tree/main/plugins/google_meet
Command: npx skills add https://github.com/MarbleSodas/Mavis --skill google-meet-marblesodas

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the manual effort of taking live notes from Google Meet by automatically joining a meeting and turning live captions into a usable transcript.

Core Features & Use Cases

  • Transcribe-only notes: Joins an explicit Meet URL and scrapes live captions into a transcript file for later summarization and follow-ups.
  • Realtime in-call responses (optional): In realtime mode, the agent can speak into the meeting using OpenAI Realtime, enabling note-taker or responder behavior during the call.
  • Optional remote node execution: Runs the browser and meeting bot on a separate approved machine to reuse the user’s signed-in Chrome profile.

Quick Start

Enable the plugin and join a meeting for automatic caption transcription by running: Hermes meet join https://meet.google.com/abc-defg-hij.

Frequently Asked Questions about google_meet

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

FAQPage Schema
How do I automatically transcribe a Google Meet call into a transcript?▼

To transcribe a Google Meet call, you can use a tool that joins the meeting via a meet.google.com URL and scrapes live captions into a running transcript file stored in your workspace for later summarization.

Can an AI agent speak during a Google Meet session in realtime?▼

Yes, an AI agent can speak during a Google Meet session by enabling realtime mode, which uses OpenAI Realtime and an audio bridge to deliver spoken responses directly into the active call.

How do I extract action items from meeting standups using automated note-taking?▼

Automated note-taking tools extract action items from meeting standups by joining the call, converting live captions into a continuous transcript, and then summarizing the text for follow-up tasks.

Do I need a specific browser environment to run a Google Meet transcription bot?▼

You can run a Google Meet transcription bot locally using a browser automation framework like Playwright, or optionally execute it on a separate approved remote node to reuse a signed-in Chrome profile.

Can I manage multiple active meeting sessions for realtime voice transcription?▼

Realtime voice transcription tools typically manage a single active session at a time, validating explicit meet.google.com URLs to ensure reliable caption scraping and audio bridge connections.

What is the best way to write meeting recaps from live Google Meet captions?▼

The best way to write meeting recaps from live Google Meet captions is to automate caption scraping into a transcript file, which you can then process for summarization and action-item extraction.