skills.rest
johan-Rm
johan-RmCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

embedded-captions

Generate occlusion-aware captions for talking-head videos using local AI matting and transcription.

Updated May 6, 2026
Search Tags:#video#subtitles#captions#cinematic#occlusion#motion-graphics#matting
One-click install
npx skills add https://github.com/johan-Rm/agents --skill embedded-captions-johan-rm
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: embedded-captions
Source: https://github.com/johan-Rm/agents/tree/main/skills/embedded-captions
Command: npx skills add https://github.com/johan-Rm/agents --skill embedded-captions-johan-rm

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill solves the problem of flat, unengaging subtitles by providing a professional-grade, occlusion-aware captioning system that integrates text directly into the scene behind the subject.

Core Features & Use Cases

  • Occlusion-Aware Compositing: Uses AI-based matting to place text behind the subject, creating a depth-sandwich effect.
  • Identity-Based Styling: Offers 36 distinct visual identities (from cinematic neon to formal documentary) to match the tone of any video.
  • Use Case: Perfect for creators producing high-end talking-head content, tech explainers, or social media reels who need "VFX-grade" captions that don't obscure the speaker's face.

Quick Start

Use the embedded-captions skill to initialize a new project for the video file source.mp4 and prepare the assets for captioning.

Frequently Asked Questions about embedded-captions

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

FAQPage Schema
How do I add subtitles behind a subject in a video without obscuring their face?▼

Occlusion-aware video captions use local AI matting to composite text behind the subject, creating a depth-sandwich effect. This ensures subtitles integrate directly into the scene without blocking the speaker's face.

How do I automatically generate and style subtitles for talking-head videos locally?▼

You can automate cinematic caption generation by running local instances of whisper for transcription, ffmpeg for processing, and hyperframes for compositing. This end-to-end pipeline operates entirely without external API dependencies.

Do I need an external API to generate cinematic motion graphics captions?▼

No external API is required. The captioning process relies entirely on local execution using hyperframes, ffmpeg, and whisper to handle AI matting, transcription, and video processing natively on your machine.

What is the best way to get VFX-grade captions for professional social media reels?▼

Using an occlusion-aware captioning system provides VFX-grade results by applying identity-based styling with 36 visual presets. It matches tones from cinematic neon to formal documentary for high-end social media content.

Can I use node and ffmpeg to automate occlusion-aware text compositing?▼

Yes, the system uses node scripts to orchestrate ffmpeg, whisper, and hyperframes. This automates AI matting and text compositing to place captions behind subjects seamlessly within the local environment.

Related Skills

Explore More Design & Creative Skills→
xingBaGanxingBaGan

video-understand

Analyze video content and transcribe audio locally with ffmpeg and Whisper.

Community
Intermediate
sunnypatneedisunnypatneedi
11

ugc-content-creator

Generate short-form video scripts with hooks, storytelling, and CTAs.

Community
Basic
chmonitorchmonitor
255

embedded-captions

Composite WhisperX-derived captions behind speakers in videos using ffmpeg matte occlusion.

Official
Advanced
kofiarhinkofiarhin

hyperframes

Create timed HTML video compositions with GSAP animations and WCAG contrast validation.

Community
Advanced