google_meet

Transcribe live Google Meet captions into structured transcript files.

3|1|Updated Jul 2, 2026
One-click install
npx skills add https://github.com/EntroVyx/hermes-agent-offsec --skill google-meet-entrovyx
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: google_meet
Source: https://github.com/EntroVyx/hermes-agent-offsec/tree/main/plugins/google_meet
Command: npx skills add https://github.com/EntroVyx/hermes-agent-offsec --skill google-meet-entrovyx

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, websockets, pulseaudio-utils, ffmpeg, and includes scripts (resource) components.

What problem does it solve?

This Skill solves the challenge of manually documenting meetings and managing real-time participation, ensuring that every discussion is captured accurately and the agent can contribute effectively without human intervention.

Core Features & Use Cases

  • Live Transcription: Automatically joins Google Meet calls to scrape live captions into a structured transcript file.
  • Real-time Interaction: Enables the agent to speak in meetings using OpenAI Realtime voice synthesis when configured.
  • Use Case: Use this during a project standup to have the agent take notes, summarize action items, and even respond to questions in real-time, allowing you to focus entirely on the conversation.

Quick Start

Use the google_meet skill to join the meeting at the provided URL and begin 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 meeting notes?

You can automate Google Meet transcription by using Playwright to join the meeting URL and scrape live captions into a structured transcript file. This allows the agent to automatically document discussions and track action items for remote teams without manual intervention.

Can an AI agent participate and speak in Google Meet calls in real-time?

Yes, an AI agent can speak in real-time during Google Meet calls using OpenAI Realtime voice synthesis. When configured with optional audio bridging, the agent can answer questions and interact with participants dynamically during the video conference.

Do I need Playwright and audio bridging to capture live captions from Google Meet?

Playwright is required for browser automation to join calls and scrape live captions. Audio bridging via PulseAudio utilities and FFmpeg is optional, required only if you want to enable duplex voice communication and real-time voice interaction capabilities.

What is the best way to track action items and generate follow-ups from video conferences?

The best way to track action items from video conferences is automating live caption scraping into a structured transcript. This enables automated meeting documentation, action item tracking, and downstream follow-up workflows for remote teams to review after the call.

How does real-time voice interaction work during a project standup?

Real-time voice interaction works by bridging audio streams during a Google Meet call and using voice synthesis. This allows the agent to take notes, summarize action items, and verbally respond to participant questions, letting you focus entirely on the conversation.