talking-head-recut

Annotate video transcripts with timed graphic overlays using ffmpeg and Whisper.

Updated Aug 23, 2026

Search Tags:#education #video annotation #interactive video #graphic overlays #transcript synchronization

Ready to run

npx skills add https://github.com/jpratt9/dotfiles --skill talking-head-recut-jpratt9

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: talking-head-recut
Source: https://github.com/jpratt9/dotfiles/tree/main/.agents/skills/talking-head-recut
Command: npx skills add https://github.com/jpratt9/dotfiles --skill talking-head-recut-jpratt9

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ffmpeg, hyperframes, whisper, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill turns talking-head videos into interactive experiences with timed, designed graphic overlays that synchronize with the transcript, making them more engaging and informative.

Core Features & Use Cases

Video Annotation: Create timed, designed graphic overlays that appear in sync with the video's transcript.
Customization: Customize the style, layout, and content of the overlays to fit your specific needs.
Use Case: Imagine you have a video interview with a subject. Use this Skill to overlay relevant data points, quotes, or timestamps to enhance the viewer's understanding and engagement.

Quick Start

Run the "talking-head-recut" skill and follow the prompts to select your video file, choose the desired output aspect ratio, and select the visual style and layout of the overlays.

Frequently Asked Questions about talking-head-recut

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

FAQPage Schema

How do I add dynamic graphic overlays to video transcripts?▼

Add dynamic graphic overlays to video transcripts by running the talking-head-recut skill, which uses Whisper for transcription and hyperframes to synchronize visual styles and layouts with the spoken text.

What is video transcript synchronization and how does it enhance educational content?▼

Video transcript synchronization aligns timed graphic overlays with spoken words, transforming static talking-head videos into interactive educational experiences that improve viewer engagement and comprehension.

Do I need ffmpeg and Whisper installed to annotate videos with timed overlays?▼

Yes, you need ffmpeg for video processing, Whisper for transcript generation, and hyperframes for applying the dynamic graphic overlays to successfully execute the video annotation workflow.

Can I customize the visual style and layout of interactive video overlays?▼

Yes, you can customize the visual style, layout, and motion patterns of graphic overlays during the skill setup to create tailored interactive experiences for your specific video production needs.

What's the best way to create interactive video experiences from talking-head interviews?▼

The best way to create interactive video experiences from interviews is using transcript synchronization to overlay relevant data points and quotes dynamically, requiring ffmpeg and hyperframes for processing.

Can this video annotation skill handle live event streaming workflows?▼

The video annotation skill applies to live event streaming workflows, supporting various visual styles and motion patterns to generate interactive experiences from talking-head video content.