google_meet

Automate joining Google Meet calls, transcribing captions, and speaking via OpenAI Realtime.

Updated Jun 9, 2026
One-click install
npx skills add https://github.com/zhouboyu-xreal/Hermes-Memory --skill google-meet-zhouboyu-xreal
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: google_meet
Source: https://github.com/zhouboyu-xreal/Hermes-Memory/tree/main/plugins/google_meet
Command: npx skills add https://github.com/zhouboyu-xreal/Hermes-Memory --skill google-meet-zhouboyu-xreal

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates joining, transcribing, and speaking in Google Meet calls, saving time and streamlining communication workflows.

Core Features & Use Cases

  • Join Google Meet Calls: Automatically join meetings based on provided URLs.
  • Transcription: Generate transcripts of the live captions from Google Meet calls.
  • Real-time Voice: Speak in real-time during the meeting using OpenAI Realtime.
  • Use Case: Imagine you're in a remote meeting and need to take notes and respond in real-time. Use this Skill to join the meeting, transcribe the captions, and speak directly to the meeting participants.

Quick Start

Use the google_meet skill to join a Google Meet call at 'https://meet.google.com/abc-defg-hij'. You can also specify the mode ('transcribe' or 'realtime') and duration to customize the behavior.

Frequently Asked Questions about google_meet

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

FAQPage Schema
How do I automate joining a Google Meet call and transcribing the meeting audio?

Automating Google Meet transcription involves providing a meeting URL to the skill, which uses Playwright to join and captures live captions to generate a text transcript automatically.

How does real-time voice interaction in Google Meet work using OpenAI?

Real-time voice interaction in Google Meet uses the OpenAI Realtime API to process captured meeting captions and generate immediate audio responses, allowing automated participants to speak directly during the call.

Do I need an OpenAI API key to use real-time voice responses in Google Meet?

Yes, an OpenAI API key is required for real-time voice responses. The skill uses the OpenAI API to generate and deliver live audio interactions during the Google Meet session.

Can I use Playwright to capture live captions for automated note-taking?

Yes, Playwright can be used to automate joining a Google Meet session and capture live captions, which are then processed to generate automated meeting notes and transcripts for remote participation.

What is the difference between transcribe mode and realtime mode for meeting automation?

Transcribe mode focuses on joining the call and capturing captions to generate text transcripts, while realtime mode adds the ability to speak and provide live audio responses using OpenAI during the meeting.

Are there limitations when automating remote participation in Google Meet?

Limitations include requiring a valid OpenAI API key for voice features and relying on visible live captions within the Google Meet interface for accurate transcription and real-time response generation.