ForkFree

Prompts / Writing

Re-cut Captions for Different Screen Shapes

You get a transcript re-cut into short, readable captions for a specific screen shape, with no change to the words. It works because the prompt gives clear reading rules (no weak-word line endings, one speaker per caption, breaks at pauses) and asks the model to check its own work against them.

Worked in our testThe reply keeps every word, stays within 22 characters and two lines, splits at the speaker change, tags names and gives a correct count of 8. It splits "forty-two" from "ceramic mugs" across captions, and it runs "everyone." into the next sentence instead of breaking at the pause.

The prompt

Act as a professional caption editor who lays out subtitles so they are easy to read on different screens.

Task: Re-cut the transcript below into captions for the screen shape {screen_shape}, keeping every word exactly as written.

Transcript:
{transcript}

Speakers and context: {speaker_notes}

Steps:
1. Keep the wording unchanged. Work within a limit of {line_limit} characters per line and two lines per caption.
2. Start a new caption whenever the speaker changes, so two people never share one caption.
3. Never end a line on a weak word such as "the", "of", "a", "and" or "to". Keep names, numbers and short phrases together on one line.
4. Treat pauses, hesitations and changes of thought as natural line or caption breaks.
5. Check each caption against steps 2 to 4 and fix any that fail.

Output: The captions only, each caption separated by a blank line, with the speaker's name in square brackets before their first caption. Then add one line saying how many captions you made and listing any you could not cut cleanly.

Change the parts in curly braces. Use it when the same video needs captions for both widescreen and vertical social formats, or when auto-generated subtitles break lines awkwardly.

What happened when we ran it

We sent

Act as a professional caption editor who lays out subtitles so they are easy to read on different screens.

Task: Re-cut the transcript below into captions for the screen shape 9:16 vertical phone video, keeping every word exactly as written.

Transcript:
Welcome back to the shop floor, everyone. Today Priya is going to show us how she packs an order of forty-two ceramic mugs in under ten minutes. Thanks, Tom. The trick is to start with the heaviest boxes at the bottom. Um, well, actually, let me show you first.

Speakers and context: Two speakers: Tom Hargreaves (host) and Priya Nair (warehouse supervisor). Video is for a small online ceramics business in Stoke-on-Trent.

Steps:
1. Keep the wording unchanged. Work within a limit of 22 characters per line and two lines per caption.
2. Start a new caption whenever the speaker changes, so two people never share one caption.
3. Never end a line on a weak word such as "the", "of", "a", "and" or "to". Keep names, numbers and short phrases together on one line.
4. Treat pauses, hesitations and changes of thought as natural line or caption breaks.
5. Check each caption against steps 2 to 4 and fix any that fail.

Output: The captions only, each caption separated by a blank line, with the speaker's name in square brackets before their first caption. Then add one line saying how many captions you made and listing any you could not cut cleanly.

The model replied

[Tom Hargreaves] Welcome back to the shop floor, everyone. Today Priya is going to show us how she packs an order of forty-two ceramic mugs in under ten minutes. [Priya Nair] Thanks, Tom. The trick is to start with the heaviest boxes at the bottom. Um, well, actually, let me show you first. 8 captions made; none that could not be cut cleanly.

Run on Claude Sonnet 5.5, 10 Nov 2026. Automatic check: 4 out of 5.

Mentioned for

ChatGPT, Claude, Gemini

Where it came from

Found on Hacker News, shared by rvanderlinden: Show HN: Overtone – Transcribe, correct and cut captions for any screen shape.

This is our own version of the idea, written and tested by us. The original may differ.

More writing prompts

Writing Struggled in our test
Rewrite Machine-Sounding Text Without Inventing Facts

You get a rewrite that sounds like a person wrote it, with a clear list of what was changed. The locked fact list stops the model inventing statistics or stories to seem more human.

Found on GitHub, shared by yucezerey
Writing Worked in our test
Add One Missing Requirement to Drafts

You get one targeted addition to your prompt instead of a full rewrite, with a reason for it. It works because the AI must first list what is already good, so your original wording and constraints are preserved.

Found on GitHub, shared by dbcaskml183-dotcom
Writing Worked in our test
Stretchtext Replies With Expandable Detail

You get a short answer that grows in controlled layers, with each new addition highlighted so nothing is repeated or lost. It works because each level is forced to keep the earlier words, so the reader stays oriented as detail is added.

Found on GitHub, shared by pro-vi