google_meet

Join Google Meet calls, transcribe live captions, and speak via OpenAI Realtime.

1|1|Updated May 9, 2026
One-click install
npx skills add https://github.com/ldzhhxx/Hermes_offline_v2 --skill google-meet-ldzhhxx
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: google_meet
Source: https://github.com/ldzhhxx/Hermes_offline_v2/tree/main/hermes-agent/plugins/google_meet
Command: npx skills add https://github.com/ldzhhxx/Hermes_offline_v2 --skill google-meet-ldzhhxx

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, websockets, pactl, blackhole-2ch, ffmpeg, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill allows the Hermes agent to join Google Meet calls, transcribe live captions, speak in real-time, and perform follow-up actions, reducing the need for manual attendance and note-taking.

Core Features & Use Cases

  • Join Meet Calls: Automatically join a specified Google Meet call and begin scraping live captions.
  • Transcription: Capture live captions from the meeting and store them for future reference.
  • Real-time Speech: Enable the agent to speak in real-time during the meeting using OpenAI Realtime.
  • Remote Node Host: Run the bot on a different machine, such as a user's Mac, for more flexible deployment options.
  • Use Case: A user can ask the agent to join a meeting, take notes, summarize the discussion, and follow up on action items without manual intervention.

Quick Start

Use the google_meet skill to join a Google Meet call 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 Google Meet attendance and capture live captions for transcription?

Automating Google Meet attendance and transcription is achieved by joining the call via a signed-in Chrome instance and scraping live captions. The agent captures and stores the discussion for future reference without manual note-taking.

Can I use an agent to speak in real-time during a Google Meet call?

Yes, real-time speech during a Google Meet call is enabled using OpenAI Realtime integration. This allows the agent to actively interact and speak aloud while attending the meeting session.

What are the requirements for joining a Google Meet call with an agent?

Joining a Google Meet call requires a signed-in Chrome instance, access to the specific Google Meet URL, and dependencies like Playwright and websockets. Local and remote node hosting configurations are supported for flexible deployment.

How does automated meeting transcription handle follow-up actions after the call?

Automated meeting transcription handles follow-up actions by summarizing the captured live captions and discussing action items. The agent processes the stored transcription to generate follow-up tasks without manual intervention.

Can I host the Google Meet transcription agent on a remote machine?

Yes, the Google Meet transcription agent supports remote node hosting configurations. You can run the bot on a different machine, such as a Mac, to provide more flexible deployment options.

What dependencies are needed for real-time speech and meeting transcription?

Real-time speech and meeting transcription require dependencies including Playwright, websockets, pactl, blackhole-2ch, and ffmpeg. These tools facilitate browser automation, audio routing, and real-time processing.