Two-person dialogue / skit: structure, script and how to clone it

Two-person dialogue / skit is a proven short-video structure. Here is why it holds attention, how its beats are timed, a script you can start from, and the command that clones it for your own subject.

Why this format works

Dialogue formats hold attention because the viewer follows a relationship, not a claim. Two voices disagreeing is the cheapest way to create tension without any production budget.

Structure breakdown

1. 1. Cold line (0–3s)

   Start inside the argument. No introductions, no scene setting.

2. 2. Claim (3–12s)

   One speaker states something confident and slightly wrong.

3. 3. Pushback (12–30s)

   The other contradicts it with a specific — a number, a name, a date.

4. 4. Flip (30–45s)

   The first speaker concedes, then lands a counter that reframes the topic.

5. 5. Cut (last 2s)

   End on the counter. No resolution needed; unresolved arguments get comments.

A script you can start from

Segments, takes and selection anchors — this is the part of the project that changes when you re-run the format:

<script>
<segment> id="claim">
  <take>Everyone says || @just-post post more. || <S | Ess> No. || Post less || @one-thing and make one thing worth watching.</take>
</segment>
</script>

What you need

• — Two voices (one person can voice both)
• — A disagreement worth having
• — Role cues so the layout knows who talks

Run it

hypit run clone --reference ./reference/dialogue.mp4 --script ./dialogue.svs --variants 4

The reference video stays fixed. Change the script, re-run, and you get a new edit in the same format — that is the whole point of cloning instead of prompting.

Keep reading

• All clone formats
• Use cases
• Comparisons
• Quickstart
• Glossary

FAQ