Does it require a paid API for transcription?

No, it prioritizes free caption extraction and local Whisper processing (MLX-Whisper or Whisper-cpp), which runs directly on your hardware.

What tools do I need to install for local transcription?

For local processing, it is recommended to have youtube-transcript-api (Python), MLX-Whisper (for Mac users), or Whisper-cpp installed as MCP tools.

How does it handle very long videos?

The skill includes token optimization strategies such as removing timestamps and splitting text into 10K character chunks to fit within AI context windows.

Which video platforms does this skill support?

It primarily supports YouTube via caption APIs and any video source (including local files) via local Whisper AI transcription models.

Video Transcript Extraction

Name: Video Transcript Extraction
Author: bogheorghiu

bybogheorghiu

0•

웹 스크래핑 및 데이터 수집

Extracts text transcripts from YouTube, local files, and other video platforms using automated detection and local Whisper AI processing.

This skill provides Claude with a robust toolkit for converting video content into searchable text across various platforms. It intelligently selects the most efficient extraction method, prioritizing fast API-based caption retrieval for YouTube before falling back to high-accuracy local transcription via Whisper (MLX or C++). Designed for research and analysis, the skill includes built-in token optimization strategies like timestamp removal and chunking to ensure cost-effective processing of large media files while integrating seamlessly with your local development environment.

주요 기능

010 GitHub stars

02Bulk processing support for handling multiple video IDs in a single workflow.

03Platform-aware extraction for YouTube, local files, and web video sources.

04Token optimization tools to reduce context usage by stripping timestamps and chunking text.

05Integrated local Whisper support for Apple Silicon (MLX) and cross-platform systems.

06Multi-method fallback logic prioritizing speed and resource efficiency.

사용 사례

01Analyzing video content for specific keywords or sentiment without manual viewing.

02Generating clean text summaries of local video recordings for documentation purposes.

03Building a searchable knowledge base from a collection of technical tutorials or lectures.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add bogheorghiu/ex-cog video-transcript-extraction

For use in Claude.ai and ChatGPT

주요 기능

010 GitHub stars

02Bulk processing support for handling multiple video IDs in a single workflow.

03Platform-aware extraction for YouTube, local files, and web video sources.

04Token optimization tools to reduce context usage by stripping timestamps and chunking text.

05Integrated local Whisper support for Apple Silicon (MLX) and cross-platform systems.

06Multi-method fallback logic prioritizing speed and resource efficiency.

사용 사례

01Analyzing video content for specific keywords or sentiment without manual viewing.

02Generating clean text summaries of local video recordings for documentation purposes.

03Building a searchable knowledge base from a collection of technical tutorials or lectures.