video-cleaning

Community

Automated video transcription and conservative editing.

Authorjykim
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Raw Korean videos often contain long pauses and filler words. This skill provides a conservative, safe editing workflow to remove dead air while preserving meaning.

Core Features & Use Cases

  • Transcription with timestamps: Uses Whisper for word-level timing to pinpoint edits.
  • Conservative editing: Removes long pauses and clear fillers (e.g., 어, 음, 아) without over-editing.
  • Report generation: Produces a detailed edit report with time savings and segment recap.
  • Use Case: Produce a concise, natural-sounding video from a long lecture recording.

Quick Start

  1. Transcribe: python transcribe_video.py "presentation.mp4"
  2. Preview edits: python edit_video_remove_pauses.py "presentation.mp4" --preview
  3. Create edited video: python edit_video_remove_pauses.py "presentation.mp4"

Dependency Matrix

Required Modules

openairequests

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: video-cleaning
Download link: https://github.com/jykim/claude-obsidian-skills/archive/main.zip#video-cleaning

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository