๐ŸŽฏ

talking-head-recut

๐ŸŽฏSkill

from heygen-com/hyperframes

VibeIndex|
What it does
|

A Claude Code skill that layers timed, designed graphic overlay cards (titles, lower-thirds, data callouts, quotes, side panels, picture-in-picture) onto existing talking-head or interview videos, synced to the transcript via the hyperframes CLI.

Overview

Talking Head Recut is a Claude Code skill for packaging existing talking-head, interview, or podcast videos with professionally designed graphic overlay cards. Rather than editing the source video itself, the skill layers timed visual elements on top of the playing video: titles, lower-thirds, data callouts, quotes, side panels, and picture-in-picture compositions. It uses local Whisper transcription to analyze what is being said, then the agent designs each card's HTML directly in conversation before rendering the final composition to MP4 via the hyperframes CLI. No external API keys are needed for transcription.

Key Features

  • Transcript-synced graphic cards: Automatically transcribes audio with local Whisper, then designs overlay cards timed precisely to what the speaker is saying
  • Flexible card types: Supports fullscreen hero moments, lower-third annotations, side panels with data, whiteboard-area dense content, and transparent video overlays with no fixed archetype constraints
  • Full HTML/CSS/GSAP control: Each card is authored as an HTML fragment with custom styling, GSAP animations, and theme-aware accent colors, giving complete creative freedom
  • End-to-end pipeline: Handles the entire workflow from audio extraction, transcription, storyboard planning, card HTML authoring, composition assembly, to final MP4 rendering
  • Local-first processing: Transcription runs via bundled Whisper with no third-party API, no rate limits, and no keys required; rendering uses system ffmpeg and a headless browser

Who is this for?

  • Content creators who want to add professional on-screen graphics to interview or podcast clips without using traditional video editing software
  • Marketing teams packaging talking-head videos with branded overlays, data callouts, and quote cards for social media distribution
  • Developers and technical communicators who want AI-assisted video packaging with full control over the HTML/CSS design of each graphic element
๐Ÿ“ฆ

Same repository

heygen-com/hyperframes(48 items)

talking-head-recut

Installation

Vibe Index InstallInstalls to .claude/skills/
npx vibeindex add heygen-com/hyperframes --skill talking-head-recut
skills.sh Installโš  Installs to .agents/skills/
npx skills add heygen-com/hyperframes --skill talking-head-recut
Manual InstallCopy SKILL.md content and save to the path below
~/.claude/skills/talking-head-recut/SKILL.md

SKILL.md

87,298Installs
-
AddedJun 26, 2026

More from this repository10

๐ŸŽฏ
hyperframes-cli๐ŸŽฏSkill

CLI tool for the Hyperframes video rendering framework that provides commands to create, preview, lint, and render HTML-based video compositions to MP4.

๐ŸŽฏ
hyperframes๐ŸŽฏSkill

Skill for authoring HTML-based video compositions with the Hyperframes framework, covering captions, TTS, audio-reactive animation, and transitions for AI agent-driven video creation.

๐ŸŽฏ
hyperframes-registry๐ŸŽฏSkill

Skill for installing blocks and components into Hyperframes projects via the `hyperframes add` command, providing access to 50+ ready-to-use overlays, shader transitions, and data visualizations.

๐ŸŽฏ
remotion-to-hyperframes๐ŸŽฏSkill

A skill for the HyperFrames open-source video rendering framework that teaches AI agents to write correct HTML-based video compositions and GSAP animations, enabling them to render video from HTML code.

๐ŸŽฏ
hyperframes-core๐ŸŽฏSkill

The foundational technical contract for HyperFrames HTML video compositions, defining data attributes, clip/track structure, sub-compositions, variables, media playback, deterministic rendering rules, and project validation.

๐ŸŽฏ
hyperframes-animation๐ŸŽฏSkill

Comprehensive animation skill for HyperFrames providing atomic motion rules, multi-phase scene blueprints, scene transitions, motion-design techniques, and seven runtime adapters including GSAP, Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, and TypeGPU.

๐ŸŽฏ
hyperframes-creative๐ŸŽฏSkill

Non-animation creative direction for HyperFrames videos covering design specs, color palettes, typography, narration scripting, beat planning, audio-reactive visuals, composition patterns, and brand/style decisions.

๐ŸŽฏ
media-use๐ŸŽฏSkill

Resolves media needs (background music, sound effects, images, icons) into frozen local files by searching the HeyGen catalog, downloading the best match, and registering it in a manifest. One resolve command handles the full cascade from cache lookup to provider search to file freezing.

๐ŸŽฏ
hyperframes-media๐ŸŽฏSkill

A media framework by HeyGen for building interactive video experiences with composable frames and real-time rendering capabilities.

๐ŸŽฏ
general-video๐ŸŽฏSkill

A fallback HyperFrames composition authoring skill for custom video creation when no specialized workflow fits. Handles multi-scene pieces, brand reels, montages, title cards, motion posters, static loops, and freeform compositions at any length or format.