Script free with an account·render in about a minute·no watermark on any plan
Script to Video Generator
You wrote the script. This cuts it into scenes, reads it in a real voice and puts a frame behind every line.
Start free — no credit card, and the script and the shot list cost no credits.
01Paste the script. Exactly as you want it read. Line breaks are honoured as hints about where the beats fall.
02It is split, not rewritten. Your wording is kept. The split is where the ideas change, and each scene gets an image prompt drawn from its own line.
03Recorded and cut to the read. The voice performs your script, every scene runs exactly as long as its line does, and captions are timed to the audio.
Voice:
Josh
Captions:
Bold
Music:
Lo-fi
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
Nobody tells you this about your first year freelancing. T…
Style: Documentary
Voice: Josh
Captions: Bold
Ratio: 9:16
A mock-up of the frame and caption layout at this page’s settings — TikTok, Reels and Shorts, lo-fi 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
“Nobody tells you this about your first year freelancing. The work is not the hard part. Finding the work is not the hard part either. The hard part is that every week you are three different people: a salesperson on Monday, a craftsman on Wednesday, an accountant on Friday. And nobody warns you that switching between them is the actual job.”
Plus this page’s brief, verbatim
Split this script into scenes. Keep the writer’s wording as close to the original as you can — this is a production job, not a rewrite. Only trim what is unspeakable out loud.
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
The preset that does not rewrite you
Every tool on this site runs the same scriptwriter with a different brief. This one’s brief is the shortest and the strictest: split, do not rewrite. It is told to keep your wording as close to the original as possible and to trim only what cannot be said out loud.
That matters because a script is usually the part a writer is proudest of, and an AI that helpfully improves your sentences is worse than useless — it has taken away the one thing you did not need help with.
02
The script is the timeline
There is no track view here, because for this kind of video there does not need to be one. Scene length is narration length: a scene runs exactly as long as its line takes to say, which is a number that comes back from the voice model with the audio rather than being estimated.
The consequence is that editing the script edits the cut. Shorten a sentence and the scene shortens. Split a sentence in two and you get two scenes with two frames. You are editing the video by editing the words, which is the fastest editing interface there is for anything that is fundamentally spoken.
03
Reading your script out loud, on purpose
A script that has never been read aloud always has three sentences in it that do not work. Tongue-twisters, clauses too long to say in one breath, a number that is ambiguous when spoken.
The free preview on this page is the cheap way to find them: it comes back with the scene split and the estimated runtime per scene before anything is generated. A scene that estimates far longer than its neighbours is usually a sentence that needs cutting in half.
Who this is for
Four people this was built for
Copywriters
You are hired for the words. This produces the video without touching them.
YouTubers repurposing a long-form script
Lift the best ninety seconds out of a twelve-minute video and post it as a short the same day.
Agencies with approved copy
The client signed off on the script. Rewriting it in production is not an option, so nothing here does.
Podcasters
The cold open you already wrote, as a vertical clip that points at the episode.
Compared
What this replaces
Six things somebody has to arrange to make one short, and who arranges them.
Input
The usual way: Hand the script to an editor and explain the tone over three calls.
With Veedio: Paste it. The split, the frames and the read all come from the script itself.
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: A VO session, then a re-session when line four changes.
With Veedio: Five voices, and changing a line re-records that line only.
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, and most of it waiting on someone else.
With Veedio: About a minute, and you watch it fill in scene by scene.
Changing it
The usual way: A script change means a new record, a new cut and a new export.
With Veedio: Edit the sentence, regenerate the scene. Its neighbours are untouched.
The usual way
With Veedio
Input
Hand the script to an editor and explain the tone over three calls.
Paste it. The split, the frames and the read all come from the script itself.
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
A VO session, then a re-session when line four changes.
Five voices, and changing a line re-records that line only.
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, and most of it waiting on someone else.
About a minute, and you watch it fill in scene by scene.
Changing it
A script change means a new record, a new cut and a new export.
Edit the sentence, regenerate the scene. Its neighbours are 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.
That is this preset’s entire job — it is told to split rather than rewrite, and to change only what is unspeakable. It is still a language model, so read the returned scenes; the free preview on this page exists so you can check before you spend anything.
How long can my script be?
Aim for 100 to 160 words. That is 40 to 60 seconds at a normal speaking pace, which is where a short lives. Much longer and the scriptwriter will start cutting to keep the video under a minute.
Can I control where the scenes break?
Indirectly, and reliably enough: put each beat on its own line. Paragraph breaks are strong hints about where the ideas change, which is where the split lands.
Can I write my own image prompts?
Yes, in the editor. Every scene has an editable image prompt as well as editable text, and regenerating the visual after you change it is free.
What happens to numbers, acronyms and names?
They are spoken as written, which is usually right and occasionally not. If an acronym should be said as a word rather than spelled out, write it that way in the script — the voice reads what is in front of it.
Can I use a script I wrote for a talking-head video?
Usually, with one edit: cut the parts that only make sense with a face on screen. Anything that gestures at the camera or says “as you can see behind me” has nothing to sit behind it here.
Does it handle dialogue between two speakers?
Not well. There is one voice per video, so a two-hander is read by one person. Scripts that work here are single-narrator.
Can I hear a voice before committing?
Not on this page — synthesis costs money, and the box at the top spends none of your credits. In the app, changing the voice re-records the narration and nothing else, so trying a second voice costs nothing either.
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.