Log In Sign Up Free
🎬

AI Video Generator

Paste a script and every scene is filmed for you — AI video clips, captions and an optional voice-over, cut into a finished video.

Every shot is filmed by a model. The exact price appears here as you type. Sign in →
Shape

About AI Video Generator

Write or paste a short script and every sentence becomes a scene with its own generated clip — real motion, filmed to order, not a still image with a zoom on it. The clips are cut together in time with the narration, captioned, and handed back as one MP4.

This is the most expensive of the three video tools by a wide margin, because generated footage genuinely costs that much to make. It is built for short pieces — an opening, a hook, an establishing sequence — rather than for a ten-minute video. For anything longer, AI Image Video does the same job with generated stills at a fraction of the price.

This is the expensive one, and it should be. A generated eight-second clip costs about 5,840 tokens, and there is one clip per scene. That is why this tool stops at 6 scenes: not because a longer script takes longer — the clips are all filmed at the same time — but because a script pasted by accident should be refused rather than quoted at a number nobody meant to spend. For a longer video, the AI Image Video tool costs a fraction as much, and Script to Video costs less again.

The quote is the worst case, and you usually pay less. The price you see is calculated from the most expensive model this tool is allowed to use. Once the clips are made we know exactly what they cost, and the charge is lowered to match. Any scene that produced no clip falls back to a clean background and is not charged for at all. You are never charged more than the number on screen.

The clips have no sound, on purpose. The models can generate audio, but it would fight the voice-over and the music this tool adds underneath. So the footage arrives silent and the soundtrack is yours — a narrator you pick, a track from the library, or nothing at all. Only the finished MP4 is saved to your library; the individual clips are working files and are cleaned up.

How to use AI Video Generator

1

Paste a short script

Each sentence becomes one scene and one clip, and clips are what cost money — so a few deliberate sentences beat a page of prose here.

2

Pick a footage style

Cinematic, documentary, aerial, animation or time-lapse. The style is applied to every scene, so the shots look like they came from the same shoot.

3

Add a voice-over (optional)

Choose a voice and the script is read aloud, with each clip held exactly as long as its line takes to say. Priced separately, per character of script.

4

Render and download

The clips are all filmed at the same time, so a six-scene video takes about as long as a one-scene video. Watch the progress, then play it in the page or download the MP4.

Key Features

Real generated motion

Every scene is a filmed shot with its own camera movement, not a photograph being slowly zoomed. Where a still would read as a slideshow, this reads as footage.

All the clips at once

Scenes are filmed concurrently rather than one after another, so six of them finish in about the time one would. The wait is the slowest shot, not the sum of them.

Priced from the worst case, charged at the real one

The quote is calculated from the most expensive model the tool is allowed to use. Once the clips exist we know what they actually cost and the charge is lowered to match — never raised.

Silent footage, your soundtrack

The clips are generated without audio on purpose, so the voice-over and music you choose are the only things you hear instead of fighting a soundtrack the model invented.

Common Use Cases

  • Short hooks and openers for social video where the first three seconds decide everything
  • Establishing shots and B-roll for scenes that would be impractical to film
  • Concept and pitch pieces before anything real exists to point a camera at
  • Abstract or impossible subjects — the inside of a star, a city that was never built
  • Title sequences and ambient loops that need motion rather than information

Security & Privacy

  • Your script is sent over TLS to our video provider to film the scenes, and to our speech provider if you ask for narration. It is not used to train anything.
  • Scripts are screened before anything is charged. A script that cannot be turned into video is refused up front rather than after your tokens are spent.
  • Finished videos are saved privately to your account and are never auto-deleted — only you or an admin can remove one.
  • A finished video is served only to the account that made it. The link is not a credential anyone else can use.

Frequently Asked Questions

Tokens, and considerably more than the other two video tools. Three lines, itemised above the button before you commit: the render itself, charged by the length of the finished video; one generated clip per scene, priced by the second at the resolution you picked; and the voice-over, if you want one, per character of script.
Money, not time — the clips are all filmed at once, so six take about as long as one. Six eight-second shots is already more tokens than most balances hold, and a long script pasted by accident should be refused rather than quoted at a number nobody meant to spend.
The quote is worked out from the most expensive model the tool is allowed to use, so it is a genuine worst case. When the clips come back we know what they really cost and charge that instead. Any scene that produced no clip is not charged for at all.
Four, six or eight seconds, chosen automatically to fit the line being narrated. A scene whose narration runs longer than its clip holds the shot rather than cutting away early.
No, deliberately. Model-generated audio would clash with the voice-over and music this tool lays underneath, so the footage arrives silent and the soundtrack is entirely yours.
Yes. Generated video belongs to the account that made it. Check the rules of wherever you publish, though — some platforms require you to disclose AI-generated content.