---
url: https://superduperai.co/library/cutaway-matching-sentence-to-visual-prompt/
title: Cutaway matching: sentence to a literal visual, same place and time
description: A prompt that reads each sentence of a transcript and names the one picture that shows it, with the place and time it must come from, so the shot list is a list of things, not moods.
category: broll
platforms: [youtube, shorts, reels, tiktok]
works_with: [claude-code, claude, chatgpt, any-llm]
tags: [b-roll, cutaway, transcript, agent, matching, footage]
difficulty: intermediate
verified: false
created: 2026-11-01
skill: video-edit
---

# Cutaway matching: sentence to a literal visual, same place and time

A prompt that reads each sentence of a transcript and names the one picture that shows it, with the place and time it must come from, so the shot list is a list of things, not moods.

## Prompt

```text
For each sentence below, write the ONE cutaway that shows it literally. Output a table: # | Sentence | Visual (the object, place or action named in the sentence, as a shot: size + what is in frame) | Must come from (the place and the time window: same location, within {15} minutes of when the sentence was said) | On camera? (yes if the speaker's lips are visible in the source for this sentence; then the answer is 'no cutaway').

Rules:
- Literal, not associated. 'The bakery was closed' is a shot of the closed bakery door, not a street.
- If the sentence names nothing visible (an opinion, a feeling), write 'none' unless the previous or next sentence names something; then the cutaway spans both.
- Never propose a shot from a place the story has not reached or has left.
- One visual per sentence; if two things are named, pick the one the sentence is about.
- Mark sentences where the thing named is shown nowhere in the footage list as MISSING, so it can be filmed or generated.

Footage available (clip, place, time, one-line description):
{paste shot list}

Sentences (clip, time, text; 'lips visible' flag if known):
{paste sentences}
```

## Steps

1. Produce the footage list from the analysis sidecars or by scrubbing: clip, place, shooting time, one line of what is visible. Without it the agent proposes shots you do not have.
2. Run the prompt, then build the contact sheet of every chosen cutaway with its sentence under it and read it. Measured on one film: 12 of 54 automatic cutaways were off topic.
3. For the MISSING rows decide: film it next time, or generate a faceless clip (see the generated-vs-real rule).

## Tips

- The 'must come from' column is what separates a cutaway from stock footage. If you cannot fill it, the shot does not belong in a film about a day.
- Place cutaways in silent windows only. The 'on camera?' column exists so lips are never covered.

## 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.