An AI-powered utility that generates clean, verbatim YouTube transcripts with speaker labels using Google Gemini.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install gemini-yt-video-transcript
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install gemini-yt-video-transcript using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Gemini YouTube Video Transcript?
The Gemini YouTube Video Transcript skill is a specialized tool designed to produce high-fidelity, verbatim text from YouTube content. By leveraging the advanced processing power of Google Gemini, it goes beyond basic automated captions to deliver structured text complete with speaker labels and natural paragraph breaks. As a key component of the Openclaw Skills ecosystem, it focuses on providing clean data by intentionally omitting time codes, making the output ideal for readers, editors, and content creators.
This skill is particularly effective for users who require a high level of accuracy and readability without the clutter of technical metadata. It simplifies the transition from video content to written documentation by automating the heavy lifting of speech-to-text processing and speaker identification through a simple CLI-based workflow.
Gemini YouTube Video Transcript Use Cases
- Converting video-based technical tutorials into searchable blog posts or documentation.
- Generating verbatim records of interviews or panel discussions for qualitative research.
- Repurposing podcast video content into clean transcripts for newsletter distribution.
- Providing accessible text versions of educational videos for students and researchers.
How Gemini YouTube Video Transcript Works
- The user inputs a YouTube URL into the system.
- The skill invokes a Python script that communicates with the Google Gemini API.
- Gemini processes the audio stream to identify unique speakers and transcribe dialogue verbatim.
- The tool strips away time codes and unnecessary commentary to focus purely on the spoken word.
- The resulting transcript, starting with the video title, is saved to the local workspace or a user-defined directory.
Gemini YouTube Video Transcript Setup
To integrate this tool into your Openclaw Skills workflow, ensure you have the necessary environment variables and dependencies configured:
# Ensure Python 3 is installed on your system
# Export your Google Gemini API key
export GEMINI_API_KEY='your_api_key_here'
# Execute the script via CLI
python3 scripts/youtube_transcript.py "https://www.youtube.com/watch?v=VIDEO_ID"
Gemini YouTube Video Transcript Data Schema & Taxonomy
The skill produces a structured text output designed for immediate consumption or further processing. The data organization follows this taxonomy:
| Attribute | Description |
|---|---|
| Header | The first line contains the full YouTube video title. |
| Content | Sequential lines in the format Speaker: Text. |
| Formatting | No time codes, lists, or extra headings are included. |
| Storage | Files are auto-named and stored in the workspace out/ folder by default. |
Gemini YouTube Video Transcript Advanced Features
- Custom output routing using the --out
flag for specific file management. - Deep integration with Openclaw Skills allowing AI agents to deliver transcripts as direct attachments in chat.
- LLM-driven speaker diarization to differentiate between multiple participants automatically.
- Streamlined verbatim mode that removes AI-generated commentary or summaries for raw data integrity.
SKILL.md
Loading
Related Openclaw Skills
ElevenLabs AI Audio Skill
A comprehensive toolset for integrating ElevenLabs advanced text-to-speech, sound effects, and music generation capabilities into your AI workflows.
ElevenLabs
A versatile toolkit for programmatic AI audio generation, voice management, and usage tracking.
Printer Skill
Enables AI agents to print images and PDFs to any CUPS printer with full PPD-aware configuration support.
CodexMonitor
CodexMonitor is a specialized CLI tool for listing, inspecting, and watching local OpenAI Codex sessions on macOS.
RZL Klientenportal
Automate the exchange of receipts, invoices, and reports with your tax accountant through the RZL Klientenportal web platform.
Snapmaker 2.0 Control
A Python-powered interface to remotely monitor status, manage print jobs, and track progress on Snapmaker 2.0 3D printers.
METADATA
Featured*
