Script free with an account·render in about a minute·no watermark on any plan
AI Video Generator
Type what the video is about. Get a scene-by-scene short with AI visuals, a real voiceover and word-timed captions.
Start free — no credit card, and the script and the shot list cost no credits.
01Describe the video. One line about the subject. You are writing a brief, not a script — specificity beats length here.
02We write it and shoot it. The script comes back as five to eight scenes, each with its own spoken line and its own generated frame.
03Voice, captions, publish. Pick a voice, pick a caption style, and post it to TikTok, Reels or Shorts from the same screen.
Voice:
Rachel
Captions:
Bold
Music:
Uplifting
Format:
Vertical 9:16
What comes out
The settings this page ships with, and the shape they produce
Every example on this page is labelled with the exact configuration behind it, including the one that says it is a drawing.
Layout mock-up
Why most productivity apps make you less productive
Style: Cinematic
Voice: Rachel
Captions: Bold
Ratio: 9:16
A mock-up of the frame and caption layout at this page’s settings — TikTok, Reels and Shorts, uplifting music bed. It is a drawing, not a rendered video: we have no published render library to show you yet, and a stock clip dressed up as our output would be worth less than saying so.
Your input
“Why most productivity apps make you less productive”
Plus this page’s brief, verbatim
Write a self-contained short-form video. Open on the single most surprising or contested claim in the subject, then earn it. No preamble, no sign-off.
That string is not marketing copy — it is the instruction the script writer is given before it reads a word of yours, and it is the only thing separating this page from the other forty-seven.
The shape that comes back
Scene 1 — the hook
One line that works with no context, because the viewer arrived mid-scroll.
Scenes 2–6 — the body
One idea each, one or two spoken sentences, each with its own image prompt and its own duration.
Final scene — the close
A line that lands the point rather than asking for a follow.
Per scene — the shot
The exact image prompt the model would receive, with this page’s style suffix already appended.
This is the structure, not a saved example. The box at the top of the page writes the real one — with your wording, in about ten seconds, free once you sign in.
5–8 scenes
each with its own line, its own frame and its own length
Under 60s
cut to the narration, not to a fixed per-scene timer
Word-timed
captions burned from the voice model’s own alignment
1080-class
vertical, square or landscape — no watermark on any plan
01
A generator that makes videos, not clips
Most tools that call themselves AI video generators return four seconds of drifting imagery. That is a clip. A video is a claim, a build and a turn — a hook that stops the scroll, three or four beats that pay it off, and a last line that lands. That structure is the part that is hard, and it is what the script stage here is for.
So the first thing this produces is a script broken into scenes, each with the line that will be spoken and the frame that will be behind it. Everything after that — the images, the voice, the captions, the cut — is assembled around that structure rather than the structure being reverse-engineered from footage.
02
Why the timing is the tell
You can usually spot an AI video within two seconds, and it is almost never the images that give it away. It is the timing: captions arriving a beat behind the voice, a scene hanging for two seconds after the sentence finished, a cut landing mid-word.
Scene length here comes from the audio, not from a guess. The voice model returns a character-level alignment with the true duration of the take, which is collapsed into per-word timings and stored with the scene. The renderer cuts each scene to its own narration and burns the captions from those timings, which is why the words land with the voice instead of near it.
03
The part everyone skips: publishing
Making a video is the visible half of the job. The invisible half is exporting it, moving it to a phone, writing a caption, posting it on three platforms and then never finding out how it did.
Veedio connects to TikTok, Instagram Reels and YouTube Shorts, posts from the same screen the video was made on, and reads back views, likes and comments a few hours later. That loop is the reason to make the next one — and it is why we measure a first published video rather than a first signup.
Who this is for
Four people this was built for
Founders posting about their product
You have a hundred things to say and no time to film any of them. This turns one of them into a short between meetings.
Faceless channel operators
The format is settled and the constraint is throughput. One brief in, one publishable short out, several times a day.
Marketers testing angles
Six versions of the same claim, each with a different hook, posted and measured rather than argued about in a doc.
Writers who do not film
You can write. You cannot be bothered to light a room. The script is the input, and the camera work is somebody else’s problem.
Compared
What this replaces
Six things somebody has to arrange to make one short, and who arranges them.
Input
The usual way: A brief, a script, a shot list, a shoot day, an edit.
With Veedio: One sentence. The script and the shot list are outputs, not inputs.
Visuals
The usual way: Film it, or licence stock and hope a clip matches the line.
With Veedio: A frame generated per scene from that scene's own line.
Voiceover
The usual way: Book a VO artist, or record yourself and cut the breaths out.
With Veedio: Five ElevenLabs voices, re-recorded free whenever the line changes.
Captions
The usual way: Auto-captions that drift, then an hour nudging keyframes.
With Veedio: Burned in from the voice model’s own word alignment, so they land on the syllable.
Turnaround
The usual way: Days. Most of it is waiting on somebody else’s calendar.
With Veedio: About a minute, filling in scene by scene while you watch.
Changing it
The usual way: A new take, a re-cut, a re-export and a re-upload.
With Veedio: Rewrite the line, regenerate that one scene. Free, and the rest of the video is untouched.
The usual way
With Veedio
Input
A brief, a script, a shot list, a shoot day, an edit.
One sentence. The script and the shot list are outputs, not inputs.
Visuals
Film it, or licence stock and hope a clip matches the line.
A frame generated per scene from that scene's own line.
Voiceover
Book a VO artist, or record yourself and cut the breaths out.
Five ElevenLabs voices, re-recorded free whenever the line changes.
Captions
Auto-captions that drift, then an hour nudging keyframes.
Burned in from the voice model’s own word alignment, so they land on the syllable.
Turnaround
Days. Most of it is waiting on somebody else’s calendar.
About a minute, filling in scene by scene while you watch.
Changing it
A new take, a re-cut, a re-export and a re-upload.
Rewrite the line, regenerate that one scene. Free, and the rest of the video is untouched.
Related tools
Same engine, different preset
Twenty more pages over the same pipeline. Each one is a different brief, a different look and a different page — and each one prints its brief the way this one does.
What does the free version on this page actually do?
It runs the first stage of the real pipeline: the same scriptwriter the app uses, with this tool’s preset applied. You get the title, every scene’s spoken line, the image prompt behind it and the estimated runtime — enough to judge the video before anyone spends a credit on it.
How long can the video be?
This page writes at the default minute — five to eight scenes of one or two sentences each — and the composer offers 30 seconds, a minute, 90 seconds and 3 minutes, with the scene count following whichever you pick. Free accounts go up to a minute; paid plans to three. Nothing longer than that is something we do today.
Where do the visuals come from?
Each scene gets its own generated frame, from an image prompt written for that specific line, plus the visual style you picked. Stills get a slow Ken Burns move; where a clip generates cleanly it is used instead, and where it does not the still is kept rather than the scene failing.
Can I change the script before it renders?
Yes, and most people should. Every scene’s text and image prompt is editable in the editor, and regenerating a single scene after an edit costs nothing — that is the intended way to fix a line that reads wrong out loud.
Is the voice a real voice or a robot?
It is ElevenLabs, with five voices to choose from — warm, documentary, bright, casual and soft. Changing the voice re-records the narration only; your script and your visuals stay exactly as they are.
What aspect ratios can it output?
Vertical 9:16 for TikTok, Reels and Shorts, square 1:1 for feed posts, and 16:9 landscape for YouTube. All 1080-class, and format is not gated by plan.
Does it work for languages other than English?
Yes. Pick one of 29 languages in the composer and the script is written in it and narrated in it — the same 5 voices speak all of them, through ElevenLabs' multilingual model. The image prompts stay in English behind the scenes, because that is what the image models read; nothing about that shows up in your video.
Can it run without me?
On paid plans, yes. Auto-Mode takes a subject or an RSS feed plus a cadence and produces a video per run, optionally publishing it, using the same pipeline this page does.
Do I have to sign up to try this?
Yes, a free one. Signup takes a moment and needs no card. Once you are signed in, the box at the top writes the script and the shot list for no credits — that is the part that decides whether the video is worth making — and rendering it into a file uses the 60 free credits the account starts with, about four videos.
What does it cost after the free credits?
Starter is $19 a month, Pro $49, Studio $149. A credit is a unit of pipeline cost rather than a video, so a five-scene short costs less than a nine-scene one, and you see the estimate before you spend anything.
Do I own the videos, and is there a watermark?
You own them, on every plan including the free credits, and there is no watermark on any plan, no resolution cap and no platform withheld. Four things do follow the plan, because they are what a video costs to make: AI motion and sound effects need Starter, a presenter avatar and the choice of video model need Pro, and a free account tops out at a minute where paid plans go to three. Everything else — every voice, every language, every caption style, every aspect ratio — is the same on all of them.