edit-video

Burn subtitle markers onto video files using Remotion and Whisper API speech timing.

Updated Mar 12, 2026
One-click install
npx skills add https://github.com/sogadaiki/claude-code-skills --skill edit-video
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: edit-video
Source: https://github.com/sogadaiki/claude-code-skills/tree/main/skills/edit-video
Command: npx skills add https://github.com/sogadaiki/claude-code-skills --skill edit-video

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @remotion/install-whisper-cpp, ffmpeg, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the process of burning subtitle text onto video footage, synchronizing it with spoken words using AI-powered speech recognition.

Core Features & Use Cases

  • Automated Subtitle Burning: Overlays text markers from a script onto video.
  • Speech-to-Text Synchronization: Uses Whisper API to detect speech timing for accurate subtitle placement.
  • Video Editing Pipeline: Integrates with Remotion for rendering and includes quality gates for review.
  • Use Case: Quickly generate subtitled versions of video lectures or presentations by providing the raw video and a script file.

Quick Start

Use the edit-video skill to burn subtitle markers from the script file 'script.html' onto the video file 'raw.mp4'.

Frequently Asked Questions about edit-video

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I auto-overlay subtitles on a video using an HTML script?

You can auto-overlay subtitles by providing a raw video file and an HTML script, and the pipeline uses Whisper API for speech-to-text synchronization and Remotion for rendering the text onto the footage.

How does Whisper API speech-to-text synchronization work for video subtitles?

Whisper API detects speech timing within the video audio, allowing the pipeline to align subtitle text markers from an HTML script accurately with the spoken words during the Remotion rendering process.

Do I need ffmpeg and Remotion installed to burn subtitles onto video footage?

Yes, ffmpeg and Remotion are required dependencies, as the pipeline utilizes Remotion for rendering video and ffmpeg for media processing, alongside @remotion/install-whisper-cpp for speech recognition capabilities.

Can I add speaker information for lower-third overlays when editing video?

Yes, the pipeline supports optional speaker information to generate lower-third overlays on the video, and simultaneously produces YouTube chapter files alongside the final rendered output.

What is the best way to generate subtitled video lectures from a script?

An automated pipeline using Remotion and Whisper API is ideal, taking a raw video and HTML script to handle video preparation, subtitle alignment, rendering, and quality checks for generating subtitled video lectures.

Why does the video editing pipeline include quality checks and multiple passes?

The multi-pass pipeline includes quality gates to verify accurate subtitle alignment and rendering, ensuring the text markers synchronize correctly with the detected speech timing before outputting the final video.