---
url: https://superduperai.co/library/pov-format-script/
title: POV: a 15-second first-person scene with the text doing the storytelling
description: The POV format in which the camera is the viewer's eyes and one line of on-screen text sets the situation; the prompt writes the text, the single action and the beat where it turns.
category: formats
platforms: [tiktok, reels, shorts]
works_with: [claude-code, claude, chatgpt, any-llm]
tags: [pov, text-on-screen, no-narration, tiktok, reels, reach, script]
difficulty: beginner
verified: false
created: 2026-11-01
---

# POV: a 15-second first-person scene with the text doing the storytelling

The POV format in which the camera is the viewer's eyes and one line of on-screen text sets the situation; the prompt writes the text, the single action and the beat where it turns.

## Prompt

```text
Write a POV script for {topic}. The format works because the viewer is cast as the character in the first frame and has to stay to find out what happens to them. No narration; the on-screen text and the picture carry everything.

Structure (15 s, 9:16):
- 0-2 s PREMISE: on-screen text, max 12 words, starting with 'POV:' and naming a situation the target viewer has been in. Camera already in the scene, first person, hands visible if relevant.
- 2-9 s THE ACTION: one continuous first-person action, no cut if possible. No text.
- 9-12 s THE TURN: the thing that changes (the result, the surprise, the small disaster). On-screen text, max 6 words.
- 12-15 s BUTTON: a reaction beat held in silence, or one line of text that is a question. No CTA in this format; the product is in the scene, the comments ask about it, the answer is a comment.

Word budget: 0 spoken words. On-screen text total under 25 words. Sound: ambient room sound or one trending-style sound placeholder marked SOUND.

Write 3 premise variants (one relatable, one aspirational, one slightly absurd) and pick one. Return: the chosen premise, a 4-row table (time, what the camera sees, on-screen text, sound), and a 1-line note on how the phone is held.

Topic: {topic}
Target viewer: {who they are, the situation they recognise}
```

## Example

Topic: a 10-minute-a-day language-learning habit. Target viewer: someone who has restarted the same app four times.

Premise variants:
1. POV: it's day 31 and you still open the app before Instagram (relatable)
2. POV: you order in Portuguese and the waiter does not switch to English (aspirational)
3. POV: your streak reminder goes off during the wedding vows (absurd)

Chosen: 2.

| Time | Camera sees | On-screen text | Sound |
|---|---|---|---|
| 0-2 s | A café table, menu in hand, waiter approaching | POV: you order in Portuguese and the waiter doesn't switch to English | café ambient |
| 2-9 s | Hands put down the menu, point at an item, a nod from the waiter | (none) | café ambient, your voice low and off-mic |
| 9-12 s | Waiter walks away, the phone on the table lights up with a streak notification: 31 | he understood. day 31. | ambient |
| 12-15 s | Hands pick up the coffee, held | 10 minutes a day. that's all it was. | ambient |

Phone held at chest height with both hands, slightly tilted down so the table and hands are in frame.

## Tips

- The premise is the hook. Spend most of the time on it; the action is just proof.
- One long take beats three cuts here. A cut breaks the 'you are here' illusion.

## Works with

- Claude Code: Runs as a skill or a prompt in the terminal; can read your files and write the result.
- Claude: Paste into claude.ai or the Claude app.
- ChatGPT: Paste into ChatGPT; works with any GPT model.
- Any LLM: Model-agnostic: Gemini, Mistral, a local model.