# Caption and subtitle style system

When to use it: Give it to Claude, an FFmpeg skill or your caption tool so every video gets captions that are readable, consistent and on brand.

Works with: [ffmpeg-skill](https://agentcut.dev/tools/ffmpeg-skill/), [VectCutAPI (CapCut/Jianying API)](https://agentcut.dev/tools/vectcutapi-capcut-jianying-api/), [MCP Bridge for Adobe Premiere Pro](https://agentcut.dev/tools/mcp-bridge-for-adobe-premiere-pro/), [Remotion Agent Skills (official)](https://agentcut.dev/tools/remotion-agent-skills-official/)

Save as: brand/CAPTIONS.md

Download: https://agentcut.dev/prompts/md/ds-captions.md

~~~~markdown
# CAPTIONS.md: Caption and subtitle style system

Two modes. Pick one per video and say which in the job.

## Mode A: Subtitles (accessibility, long form, client work)
- Max 42 characters per line, max 2 lines.
- Reading speed: max 20 characters per second for adult viewers.
- Duration: min 0.83 s (20 frames at 24 fps), max 7 s.
- Gap between captions: at least 2 frames.
- Position: bottom center inside title safe. Move to top only when it would cover burned in text or a face.
- Style: [sans serif], white, 2 px black outline or a 60% black box, no animation.
- Line breaks: after punctuation, before conjunctions and prepositions. Never split a name, a number and its unit, or an article and its noun.
- Include [MUSIC] and speaker labels only when the speaker is off screen or unclear.
- Spelling: use the term list below exactly.

## Mode B: Social captions (Shorts, Reels, TikTok)
- 1 to 4 words at a time, one line, max 28 characters.
- Size: 7 to 10% of frame height on 1080x1920.
- Position: center or just below center. Never in the bottom 20% or the right 12% of the frame.
- Style: heavy weight [typeface], [white] fill, 6 to 10 px dark outline, active word in [accent #FFE600].
- Timing: word appears 1 to 2 frames after it starts in the audio. Never before.
- Motion: entrance pop 90% to 100% scale over 4 frames, or none. Choose one and keep it for the whole video.
- Emphasis: max one highlighted word per caption. Numbers and names first.

## Shared rules
- Never change what the speaker said, except removing filler words (um, uh) in Mode B when asked.
- Keep captions off faces and off on screen text.
- Deliver the caption file ([SRT / VTT / ASS]) next to any burned in version.

## Term list
| Spoken | Write |
|---|---|
| [agent cut] | [AgentCut] |
| [resolve] | [DaVinci Resolve] |
| [add yours] | |
~~~~

Sources and credit:

* [Netflix Timed Text Style Guide (English USA)](https://partnerhelp.netflixstudios.com/hc/en-us/articles/217350977-English-USA-Timed-Text-Style-Guide): Line length, reading speed and duration limits for the subtitle mode

---
AgentCut: https://agentcut.dev/ · All tools as JSON: https://agentcut.dev/tools.json · Overview for agents: https://agentcut.dev/llms.txt