AI Video Effect · Short form
Fitted Captions
Typographic captions. Each phrase becomes a justified block: one huge serif italic accent word, with the other words set in bold sans and sized so every line spans exactly the same width. You give Claude Code your video; it plans the edit, renders it on your computer and exports a finished 1080×1920 MP4.
# Fitted Captions — video style
Typographic captions. Each phrase becomes a justified block: one huge serif italic accent word, with the other words set in bold sans and sized so every line spans exactly the same width.Every paid plan opens all 18 styles.
How it works.
- 01
Add your video
Put
my_video.mp4in a folder and open that folder in Claude Code. - 02
Edit my_video.mp4 in the Fitted Captions style.Type the prompt
Paste it into Claude Code and press Enter. Claude writes a short plan first.
- 03
Get your edit
Claude edits it, checks it frame by frame and saves the finished MP4 in the Export folder.
First time? Unzip the skill into .claude/skills/ and type “Set up the Fitted Captions skill.” once.
Questions
What do I need to use Fitted Captions?
Claude Code (the desktop app's Code tab or the terminal), a Mac or Linux computer with Python 3.9+ and ffmpeg, and about 3 GB of free disk space for the speech and vision models, which download once. Then: your talking-head video. Vertical 9:16 is ideal; a horizontal recording also works.
What does Fitted Captions export?
1080×1920 (9:16), 30 fps, H.264 + AAC, ready for Reels, TikTok and Shorts.
Can I change the colours and fonts?
Yes. They live in the skill's brand settings. Tell Claude your colours and font, for example "Use my brand: #0E1A2B background, #F4EFE6 text, Gilroy font", and it updates them. The default fonts are free (SIL Open Font License).
Is my video uploaded anywhere?
No. Everything runs on your computer, and your video and voice are never uploaded. The only downloads happen during setup: Python packages, two MediaPipe models from Google, the Whisper speech model and the free fonts.
Can I use a horizontal recording?
Yes. Vertical 9:16 is ideal, but a horizontal recording also works: the skill has a fallback layout for it.
What happens when I correct something?
Claude adds your correction to the skill as a rule, so the same thing does not happen in your next edit.
What should I prepare?
Your talking-head video. Vertical 9:16 is ideal; a horizontal recording also works. Optional: screenshots, photos, logos and B-roll that support what you say.
What does Fitted Captions not do?
It edits a recording you already have. It does not write your script or film you. It runs on macOS or Linux with Python 3.9+ and ffmpeg, not on Windows. Sound effects are not included. Add your own licensed samples, or it uses clean built-in sounds.
More like this.
- Business ReelsFull screen, split screen and full-screen animation, switching on every cut.
- Explainer PanelYou in a panel at the bottom, animated explanations on top.
- Glass ExplainerThe panel edit with glass cards, counters and drawn graphs.
- B-roll and Stacked TextTight cut, B-roll, captions with stacked key phrases.
- Cut-out BackdropYou cut out over full-screen images that change with every idea.
- Cut-out GridYou in the centre of four images that change together.
- Depth UIYou full frame, real interfaces and screens behind your head.