google_meet

Join Google Meet calls, transcribe live captions, and speak in real-time using Playwright and OpenAI Realtime API.

1|1|Updated May 25, 2026
One-click install
npx skills add https://github.com/aayushsoam/clawbot-agent --skill google-meet-aayushsoam
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: google_meet
Source: https://github.com/aayushsoam/clawbot-agent/tree/main/plugins/google_meet
Command: npx skills add https://github.com/aayushsoam/clawbot-agent --skill google-meet-aayushsoam

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, websockets, openai-realtime-api, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill simplifies joining Google Meet calls, transcribing live captions, and speaking in real-time, enabling efficient communication and note-taking.

Core Features & Use Cases

  • Join Google Meet Calls: Automatically join meetings from provided URLs.
  • Transcribe Live Captions: Capture live captions from Google Meet calls into a transcript file.
  • Real-Time Speech: Speak in the meeting in real-time (requires OpenAI Realtime API key and audio bridge setup).
  • Use Case: Ideal for agents that need to sit in on meetings, take notes, summarize discussions, and respond to questions within the meeting.

Quick Start

Use the google_meet skill to join a meeting at '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 automate joining Google Meet calls and capturing live captions?

To automate joining Google Meet calls and capturing live captions, you can use a Skill that leverages Playwright to control the browser and extract real-time transcription text directly from the meeting interface into a transcript file.

Can I have an AI agent speak in real-time during a Google Meet?

Yes, an AI agent can speak in real-time during a Google Meet by utilizing the OpenAI Realtime API, provided you configure the required API key and complete the platform-specific audio bridge setup to route audio.

What do I need to set up before automating Google Meet transcription and real-time speech?

Before automating Google Meet transcription and real-time speech, you need Playwright installed, an OpenAI Realtime API key, and a configured platform-specific audio bridge to handle real-time audio input and output.

Does Google Meet transcription with Playwright require manual browser interaction?

Google Meet transcription with Playwright does not require manual browser interaction, as the automation script programmatically joins the meeting using a provided URL and captures captions in the background.

What are the limitations of using an automated agent for real-time communication in Google Meet?

Limitations of using an automated agent for real-time communication in Google Meet include dependency on a stable OpenAI Realtime API connection, the necessity of a platform-specific audio bridge setup, and potential browser automation detection.