Create your video now·render in about a minute·no watermark on any plan
AI Sci-Fi Video Generator
Type a science fiction premise, or paste the notes for a future you are building, and get a narrated short story with a cinematic scene for every beat, captioned as it is told.
01Give it a premise, or your future. A person, a machine and the thing that goes wrong, in one line, or the notes for a setting you are building, kept exactly as you wrote them.
02Read the story before it renders. The story comes back as a script, one beat per scene. Rename the ship, tighten the turn, cut a scene that explains too much.
03A cinematic scene for every beat. Each beat is generated as its own frame and set in motion, read by a deep narrator over a tense score, with captions on every word.
Voice:
Adam
Captions:
Bold
Music:
Cinematic
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
The last engineer on a generation ship finds a second crew…
Style: Cinematic
Voice: Adam
Captions: Bold
Ratio: 9:16
A mock-up of the frame and caption layout at this page’s settings — TikTok, Reels and Shorts, cinematic 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
“The last engineer on a generation ship finds a second crew asleep in a section that is not on any deck plan”
Plus this page’s brief, verbatim
Write an original science fiction story for a short narrated video, told by a narrator in the past tense, like a story told aloud. Open on the strangest true thing about this future or this moment, not on a greeting, a date or a definition. Give the main character one clear want and one problem caused by the technology, the place or the people of this future, build to a turn, and end on an image or a consequence that lands — a short story with an ending, not a trailer for one. If the user asks for a future history or a documentary, tell how one change came about as a history with one event at its centre. Invent every name, ship, planet and company; never use a character, a ship, a place or a name from an existing book, film, game or series. If the user gives setting notes, names or rules, keep them exactly and add nothing that contradicts them. Present invented technology as part of the story and never as real science, and state no real-world statistic, study or date. Keep any violence off screen and describe no gore. Put no real person on screen. Each scene is one beat of the story and describes one frame a cinematographer could show: a place, a machine, an object, weather and light, with no text, screens with writing or interface labels in the frame and no character speaking to camera.
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.
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
One idea about the future, followed to its consequence
Short science fiction works when it takes one idea seriously — a ship that outlives its crew, a city that stops answering, a machine that does exactly what it was told — and follows it to a consequence. The brief asks for that: a character with one want, a problem that comes from the future itself, a turn, and an ending that lands, told in the past tense by a narrator rather than explained like a lecture.
Ask for a future history instead and it tells how one change came about, as a documentary from further on with one event at its centre — the format sci-fi channels post as lore. The invented technology is part of the story and is never presented as real science, and the brief states no real statistic, study or date, so nothing in the video passes itself off as a fact about our world.
02
Your setting stays yours, story after story
Every name, ship, planet and company is invented for your video. The brief never borrows a character, a ship, a place or a name from an existing book, film, game or series, so what you post is yours to post. If you are building a setting of your own — for a novel, a game or a channel — paste its notes with “keep my facts”: the names of the colony, the ship and the people, and the rules of how the technology works, are kept exactly, and nothing is added that contradicts them.
The composer does not remember your setting between videos, so keep a short setting note — five or six lines of names, places and rules — and paste it with each new premise. That is what keeps a series coherent: the same colony, the same long night, the same engineer, one story a day, in the same voice and the same cinematic look.
03
What the frames can show, and what they cannot
Each scene is one cinematic frame generated from its own line — the derelict station, the red dune under two suns, the last light in a city that has gone quiet. On a paid plan each frame is set in motion by default (68 credits for a five-scene video), or choose Stills in the composer and the same video is 13 credits, as still frames with a slow pan. Every scene is drawn on its own, so the pilot in the first scene and the pilot in the last will not match exactly, a ship’s hull may change from shot to shot, and nobody on screen speaks — the narrator tells the story and there is no lip sync. Stories carried by a place, a machine and one clear turn hold together; a story that needs one face or one ship to stay identical in every shot does not.
There is no text in the frames — no readable screens, mission patches or console labels — because image models misspell them; the captions carry the words. A deep, documentary narrator reads by default over a tense cinematic music bed; 5 voices are previewed in the composer, and the look can be switched there to retro, anime or comic. There are 5 voices, all recorded in American English. There is no British, Irish or Australian voice and no voice cloning. The narration and captions can be in any of 29 languages — French, German, Spanish, Italian, Dutch and Polish among them — chosen in the composer; the voices read them, but a native listener may hear the American accent, so listen to the first one before you post a series. Every video is made on a plan: Mini is $7 a month, and the first payment on any plan has a 7-day money-back guarantee.
Who this is for
Four people this was built for
Sci-fi story and lore channels
A new story or a page of future history every day for Shorts, TikTok or Reels, in one voice and one look, set in a future you keep.
Writers testing a premise
The opening of a novel or a short story told as a one-minute short, to find out whether the idea pulls people in before you write the rest.
Game designers and game masters
The history of the station your players are about to board, or the briefing for a new campaign, played before the session.
English and creative writing teachers
A one-minute story built on one idea and its consequence, as a model of how science fiction works or as a prompt for the class to continue.
Compared
What this replaces
Six things somebody has to arrange to make one short, and who arranges them.
Input
The usual way: Write the story, then commission concept art or model the ships yourself.
With Veedio: A one-line premise, or your setting notes kept exactly.
Visuals
The usual way: Render or license a matte painting for every beat of the story.
With Veedio: A cinematic frame generated from each beat’s own line, set in motion.
Voiceover
The usual way: Book a narrator with the right gravity, and rebook for every rewrite.
With Veedio: A deep narrator by default, 5 voices to choose from, a changed line re-read on its own.
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: Re-record the line, re-cut the timeline, re-export, re-upload.
With Veedio: Edit the line and only its voice is re-recorded, free. A new still is free too; a new motion clip is free once per video.
The usual way
With Veedio
Input
Write the story, then commission concept art or model the ships yourself.
A one-line premise, or your setting notes kept exactly.
Visuals
Render or license a matte painting for every beat of the story.
A cinematic frame generated from each beat’s own line, set in motion.
Voiceover
Book a narrator with the right gravity, and rebook for every rewrite.
A deep narrator by default, 5 voices to choose from, a changed line re-read on its own.
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
Re-record the line, re-cut the timeline, re-export, re-upload.
Edit the line and only its voice is re-recorded, free. A new still is free too; a new motion clip is free once per video.
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.
Type a fantasy premise, or paste the notes for a world you are building, and get a narrated short story or legend with a cinematic painted scene for every beat, captioned as it is told.
Will the same character or ship appear in every scene?
Every scene is drawn on its own, so the pilot in the first scene and the pilot in the last will not match exactly, a ship’s hull may change from shot to shot, and nobody on screen speaks — the narrator tells the story and there is no lip sync. Stories carried by a place, a machine and one clear turn hold together; a story that needs one face or one ship to stay identical in every shot does not.
Can it use ships or characters from a film or series I love?
No. Every name, ship, planet and company is invented for your video. The brief never borrows a character, a ship, a place or a name from an existing book, film, game or series, so what you post is yours to post. Fan fiction set in someone else’s universe is theirs to license, and the brief will not write it.
Can I make a series set in my own universe?
Yes. Keep a short setting note — names, places, how the technology works — and paste it with each premise, saying keep my facts. The composer does not remember it between videos; the note is what keeps the series coherent.
Is the science in the story real?
No, and the video does not pretend it is. The technology is invented for the story, and the brief states no real-world statistic, study or date. If you want a video that explains real space or real science, the space facts and AI science pages are written for that, with the facts read before rendering.
Can the frames show screens, maps or text?
A screen can glow in a frame, but nothing on it is readable: the brief keeps text, labels and interface writing out of every frame, because image models misspell them. The captions carry every word the narrator says.
Can it be in another look than cinematic?
Yes. Switch the look in the composer — retro suits an 80s future, anime and comic suit a fast one. Each scene is one cinematic frame generated from its own line — the derelict station, the red dune under two suns, the last light in a city that has gone quiet. On a paid plan each frame is set in motion by default (68 credits for a five-scene video), or choose Stills in the composer and the same video is 13 credits, as still frames with a slow pan.
What does it cost, and how long can a video be?
Plans are monthly: Mini $7 (200 credits), Starter $19 (600 credits), Pro $49 (2,000 credits), Studio $149 (7,500 credits). A five-scene short in pictures costs 13 credits; with AI motion in every scene it costs 68. You see the price before you generate, and the first payment on any plan has a 7-day money-back guarantee. Mini ($7 a month, 200 credits) covers about 15 five-scene shorts in pictures, or about 2 with AI motion in every scene. Every paid plan makes videos of 30 seconds, one minute, 90 seconds or three minutes; a longer video has more scenes and costs more credits, and you see the price before you generate.
Can I post it to Shorts and TikTok?
Connect TikTok, Instagram and YouTube once and publish to TikTok, Reels and Shorts from the app, on every plan. Mini connects 1 account, Starter 3, Pro 6 and Studio 25. Or download the video and post it anywhere. You own the videos on every plan and can use them commercially, paid ads included. There is no watermark on any plan, the export is 1080p, and the music beds are licensed for commercial use with no attribution. There are 5 voices, all recorded in American English. There is no British, Irish or Australian voice and no voice cloning. The narration and captions can be in any of 29 languages — French, German, Spanish, Italian, Dutch and Polish among them — chosen in the composer; the voices read them, but a native listener may hear the American accent, so listen to the first one before you post a series.
Do I have to sign up to try this?
Yes, and pick a plan: Mini is $7 a month, and the first payment has a 7-day money-back guarantee. On a plan, 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.
Do I own the videos, and is there a watermark?
You own them, on every plan, 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, and a presenter avatar and the choice of video model need Pro. Everything else — every voice, every language, every caption style, every aspect ratio — is the same on all of them.