Skip to content
OpenMicroDrama

Veo 3 prompt generator

Fill in your cast and shots. You get a Veo 3.1 prompt built on Google's five-part formula, with timed cuts and quoted dialogue. Free, no sign-up. Or describe the scene in a sentence and let AI fill the form.

Describe the scene, let AI fill the form

Free, 3 a day without an account. It fills the form; you still check it.

Clip
Characters

Use the exact same look in every prompt of the episode. That's what keeps the face from changing.

Scene
Shots
Shot 1

One clear action. Show feelings through the body, not with big emotion words.

Shot 2

One clear action. Show feelings through the body, not with big emotion words.

Shot 3

One clear action. Show feelings through the body, not with big emotion words.

Veo prompt
Elena: 24-year-old woman, chestnut hair in a low ponytail, cream silk blouse, tan trench coat.
Adrian: 32-year-old man, sharp jaw, slicked-back black hair, charcoal three-piece suit, silver cufflinks.
[00:00-00:03] Medium shot, slow push in. Elena pushes the office door open and stops, holding a printed contract.
[00:03-00:05] Close-up, static camera. Adrian looks up from his desk without standing. Adrian says coldly, "You signed it without reading it?"
[00:05-00:08] Extreme close-up, slow push in. Elena's jaw tightens, her eyes wet, she doesn't blink.
Setting: a dark penthouse office with floor-to-ceiling windows, warm desk-lamp light, dark room.
Live-action, cinematic, vertical 9:16, glossy, polished interiors.
No on-screen text.
Negative prompt

subtitles, captions, on-screen text

Settings: Veo 3.1 · 9:16 · 8s · 1080p, or 720p if you'll Extend it

What it does for you

  • Follows Google's formula for each shot: camera, subject, action, setting, then style and mood.
  • Times several cuts inside one 8-second clip, like "[00:00-00:02] medium shot". They share the same cast and light.
  • Writes dialogue the way Google's guide does: Adrian says quietly, "You're late."
  • Warns you when two people speak in the same clip, and keeps the lines to one or two.
  • Switches to 8 seconds when you use reference images, because Veo requires it.
  • Lists the negative prompt as things ("subtitles, captions"), the way Google asks.

Before you hit generate

  • Open on a face or a reveal, not a slow skyline. Episodes win or lose viewers in the first three seconds.
  • Use 4- to 6-second clips for reaction cuts and keep 8-second clips for dialogue.
  • Use Extend for walk-and-talks and slow moves. It only works on 720p clips Veo made.
  • Download right away. The Gemini API deletes generated videos after two days.

Every rule here comes from our Veo guide. Want a finished prompt to start from? Browse Veo prompts by genre.

Questions

Is this Veo prompt generator free?
Yes, and there's no sign-up. The form runs in your browser. Only the AI fill sends anything: your one-sentence idea goes to our server and an AI model (Gemini, via OpenRouter, set to providers that don't keep or train on requests). We don't store it. You still pay for the video, though Google Flow gives everyone 50 credits a day.
Does it work for Veo 3?
Google shut down Veo 3 and Veo 3 Fast in the Gemini API on June 30, 2026. Veo 3.1 replaced them, so that's what this writes for. Older tutorials that use the Veo 3 model IDs won't run.
How do I write a dialogue scene with two people?
Veo can swap the lines when two people speak in one clip. Give each speaker their own clip, a shot and a reverse shot, and cut between them. The generator warns you when a clip has two speakers.
Why is my clip set to 8 seconds?
Clips that use reference images must be 8 seconds long, and 1080p and 4K only work at 8 seconds. So the generator switches to 8 seconds when you tick the references box.
Where does the negative prompt go?
Google says to list the things you don't want ("subtitles, captions") instead of writing "no subtitles". Paste the list into the negative prompt where there is one (Google Cloud, fal). On the Gemini API there's no field, so the prompt also ends with "No on-screen text."

Other prompt generators