Explainer video script prompt builder
A good explainer video earns its length — every second of narration costs the viewer attention. This tool builds an AI prompt that produces a tight, well-structured script for your chosen duration, and shows you the narration word budget so the script never runs over when read aloud.
How it works
Spoken narration averages about 150 words per minute, so length and word count are directly linked. The tool converts your chosen duration into a target word count — roughly 150 words for 60 seconds — and bakes that limit into the prompt. The prompt then asks the model for a proven explainer structure:
- Problem — a hook in the first five seconds naming the viewer’s pain.
- Solution — how your product addresses it.
- How it works — the key mechanism in plain language.
- Call to action — one clear next step.
It also requests a two-column visual and voiceover layout broken into short scenes, which is the format animators and editors actually work from.
Word budget by duration
| Video length | Target word count | Approximate scenes |
|---|---|---|
| 30 seconds | ~75 words | 3–4 scenes |
| 60 seconds | ~150 words | 5–7 scenes |
| 90 seconds | ~225 words | 7–10 scenes |
| 2 minutes | ~300 words | 10–13 scenes |
These are narration-only counts. On-screen captions, titles, and logo bumpers do not count toward the word budget but do consume screen time, so factor a 5–10 second buffer for any branded intro or outro.
Why the hook matters so much
The first five seconds determine whether most viewers keep watching. The prompt forces an opening that names the viewer’s pain specifically — not a company name or a feature list, but the problem the viewer already feels. For example, a script for an invoice tool would open with something like “If you’ve ever spent Sunday night chasing down unpaid invoices instead of doing the work you love…” rather than “Our software automates your billing workflow.” The emotional connection to a problem is what makes a viewer keep watching.
The two-column format
A two-column visual/voiceover layout is the standard handoff document between scriptwriter and animator. The left column describes what appears on screen (characters, icons, motion, text overlays). The right column contains the exact narration words. The prompt produces this format by default, which saves a rewrite step before production.
Tips and examples
Spend the most effort on the key message field — an explainer should land exactly one idea, and the script will lead with whatever you put there. Keep the audience specific so the opening hook bites; “self-employed designers who hate tax season” produces a sharper first line than “everyone”. Read the generated script aloud against a timer before recording — if it overruns, cut from the “how it works” section first, since viewers care most about the problem and the result. End on a single CTA; offering two choices reliably lowers conversion.
When reviewing the output, pay special attention to the transition between the “how it works” section and the call to action — this is where generic scripts tend to go vague. If the CTA says “try it today” without specifying what the viewer should actually do or what they get, sharpen it: “Start a free 14-day trial — no credit card needed” is actionable where “learn more” is not.