google_meet

Join Google Meet URLs and transcribe live captions via Playwright.

Updated May 15, 2026
One-click install
npx skills add https://github.com/cabezno/bmb-encover-agent --skill google-meet-cabezno
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: google_meet
Source: https://github.com/cabezno/bmb-encover-agent/tree/main/plugins/google_meet
Command: npx skills add https://github.com/cabezno/bmb-encover-agent --skill google-meet-cabezno

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve?

This Skill lets you offload meeting note-taking by automatically joining a Google Meet, capturing live captions into a transcript, and optionally speaking back in realtime.

Core Features & Use Cases

  • Live transcription from captions: Joins an explicit Google Meet URL and scrapes live captions into a transcript for later summarization and follow-ups.
  • Realtime in-call voice responses: In realtime mode, enables the agent to speak via OpenAI Realtime audio output using a virtual audio bridge.
  • Local or remote node execution: Runs on the gateway machine or on a separate approved node host that has the user’s signed-in Chrome profile.
  • Use case: Have the agent join a standup, capture who said what, then generate action items and send a recap after the call.

Quick Start

Tell the agent to join your Meet at the provided URL in transcribe mode, then poll the transcript and ask it to summarize and produce follow-up action items.

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 into a transcript?

To transcribe a Google Meet automatically, this Skill joins a specified meet.google.com URL and uses a Playwright scraper to capture live captions into a text transcript for downstream note-taking.

Can I use Google Meet captions for automated action items and follow-ups?

Yes, Google Meet captions can be used for automated action items. The Skill captures live speech into a transcript, which you can then summarize to generate structured follow-up tasks.

How does realtime voice response work during a Google Meet?

Realtime voice response during a Google Meet works by provisioning an audio bridge with OpenAI Realtime and routing the output through a virtual audio device, allowing the agent to speak in-call.

Do I need a specific browser setup to scrape Google Meet live captions?

Scraping Google Meet live captions requires a signed-in Chrome profile. The scraper runs locally via Playwright or on a remote approved node host that has your profile authenticated.

Can the agent join a Google Meet in listening-only mode for transcription?

Yes, the agent can join a Google Meet in listening-only mode by default, transcribing the call without speaking, unless you explicitly enable realtime in-call voice responses.