mcpField
V
viral-video-animated-captions

viral-video-animated-captions

github.com/josiahsiegelCreative & media59133 installsUpdated 19w ago
Repository

About viral-video-animated-captions

A skill for short-form video creators making burned-in social captions. It turns word timings into animated ASS subtitles and guides FFmpeg rendering and readability checks.

Key features

  1. 01Word- or phrase-timed captions
  2. 02Pop, bounce, scale, and karaoke effects
  3. 03Whisper timestamp-to-ASS conversion
  4. 04Platform styling and safe-zone guidance
  5. 05FFmpeg caption burn-in workflow

Use cases

  1. 01Caption TikTok and YouTube Shorts
  2. 02Create word-highlighted explainers
  3. 03Check vertical caption readability and placement

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/josiahsiegel/claude-plugin-marketplace --skill viral-video-animated-captions

After installing, type/viral-video-animated-captionsin Claude Code to confirm it loaded.

Bundled filesreferences/caption-styles-and-generation.md

Details

From the project README

CapCut-Style Animated Captions

Use this skill to create burned-in social captions with word-level timing, pop/bounce/scale animations, karaoke highlighting, and platform-appropriate caption styles. This SKILL is a lean orchestrator; detailed ASS styles, scripts, formulas, and presets are preserved in references/caption-styles-and-generation.md.

When to Use

  • Word-by-word or phrase-by-phrase social captions
  • CapCut-style pop, bounce, sweep, karaoke, and typewriter captions
  • Whisper transcript to animated ASS conversion
  • TikTok, YouTube Shorts, Instagram Reels, and Facebook Reels caption styling
  • Caption readability, safe zones, accessibility, and mobile typography

Caption Workflow

  1. Generate transcript with word-level timestamps using Whisper or another ASR tool.
  2. Convert word timings into ASS events and styles.
  3. Use ASS timing units correctly: karaoke tags use centiseconds; animation tags use milliseconds.
  4. Burn ASS into the video with FFmpeg.
  5. Verify readability, safe-zone placement, audio sync, and final platform specs.

Minimal Burn-In Command

ffmpeg -i input.mp4 \
  -vf "ass=captions.ass" \
  -c:v libx264 -preset fast -crf 23 \
  -c:a copy \
  output_captioned.mp4

If audio copy fails because the output container cannot accept the source audio, re-encode audio with -c:a aac -b:a 128k.

Quick Style Selection

StyleEffectBest for
Word PopEach word scales in with overshootHigh-energy hooks, gaming, comedy
Highlight SweepFull phrase visible, words highlight in sequenceEducational and professional explainers
Karaoke FillProgressive fill across wordsMusic, voiceover, lyric-style captions
TypewriterCharacters appear progressivelyDramatic storytelling
Bounce InWords move/scale from belowShorts/Reels emphasis beats

Timing and Readability Rules

  • Word-level animations usually need 80-250ms appear time and 200-600ms dwell, depending on platform.
  • Keep 3-6 words on screen for vertical social video.
  • Use large sans-serif fonts, high contrast, and a thick outline.
  • Avoid excessive shake/flash; keep accessibility and readability ahead of novelty.
  • Keep captions inside mobile safe zones; avoid the lower UI-heavy region.

Reference Map

  • references/caption-styles-and-generation.md - Full preserved reference: Whisper timestamp commands, ASS structure, WordPop/Sweep/Karaoke/Typewriter/Bounce examples, Python JSON-to-ASS script, bash pipeline, burn commands, style presets, color schemes, emoji integration, platform guidelines, troubleshooting, spring/easing/shake/pulse formulas, accessibility guidance, sources.

Related Skills

  • ffmpeg-captions-subtitles - Subtitle fundamentals and burn-in
  • ffmpeg-karaoke-animated-text - ASS karaoke and animated text patterns
  • ffmpeg-animation-timing-reference - Timing units, easing, readability, sync
  • viral-video-platform-specs - Export specs and safe zones
  • viral-video-hook-templates - Hook and retention strategy

Comments

Markdown supported