Create your video now·render in about a minute·no watermark on any plan
AI True Crime Video Generator
Name a well-documented historical case, or paste your own researched notes, and get a narrated true-crime short that tells what the record shows, with a cinematic scene for every beat and captions on every word.
01Name a historical case, or paste your research. One case per video, decades old and well documented — or your own notes with keep my facts, kept exactly as you wrote them.
02Check the script against the record. It comes back one beat per scene. Check every date, number and name against your source, and cut anything you cannot stand behind.
03A cinematic scene for every beat. Each beat is generated as its own frame of a place or an object and set in motion, read by a deep documentary narrator, 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 1911 theft of the Mona Lisa from the Louvre: how the p…
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 1911 theft of the Mona Lisa from the Louvre: how the painting left the museum, and the more than two years before it was found”
Plus this page’s brief, verbatim
Write a short narrated true-crime documentary about one historical case, told by a narrator in the past tense. Tell only what is well documented in court records, official reports or long-established reporting, say plainly where accounts disagree, and say so if the case was never solved. Never invent a date, a number, a quote, a motive or a detail, and attribute no words to a real person unless they are famously recorded. If the user gives facts and says keep my facts, use them exactly and add nothing that goes beyond or contradicts them. Never name anyone as guilty who was not convicted; in an unsolved case, tell each theory as a theory. Name no living private individual: refer to witnesses, relatives and bystanders by their role. If the user asks about a recent case, an open investigation or a living private person, do not write about it; write instead about how a case like it is investigated, naming nobody. Centre the story on what happened and how it was solved or why it was not, never on the suffering of victims; refer to victims with respect, describe no gore and no injury in detail, and do not dramatise a death. Open on the most surprising documented fact, not on a greeting or a warning, and end on what the case changed or what is still unknown. Each scene describes one frame: a place, a building, an object, a period street, weather and light — no real person's face, no victim, no weapon in use, no blood, no text, documents with writing or newspaper headlines 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
What the record shows, and where it runs out
A true-crime short people trust is one that knows the difference between what is documented and what is a theory. Historical cases only: the brief tells what court records, official reports and long-established reporting say about a case decades old, says where accounts disagree or where a case was never solved, and invents no date, number, quote, motive or detail. It does not write about a recent case, an open investigation or a living private person, and it names nobody as guilty who was not convicted — in an unsolved case, a theory is told as a theory.
The brief opens on the most surprising documented fact — a painting gone from its wall for a day before anyone noticed, a raft made from raincoats — and ends on what the case changed or what is still unknown, rather than on an invented twist. A case that was never solved is told as unsolved, with each theory labelled as one, because that is what it is.
02
Told with respect for the people it happened to
The story is what happened and how it was solved, or why it never was — not the suffering of the people it happened to. Victims are named with respect or not at all, nothing is gory, no injury is described in detail and no death is dramatised. Witnesses, relatives and bystanders who may still be alive are referred to by their role, never by name. That is why the examples on this page are heists and escapes: cases with a mystery and a method at their centre, which is what a minute of narration can tell well.
The frames follow the same rule. An image model will draw whatever face it is asked for, and a generated face beside a real name is a fabrication about a real person, so no real person’s face is drawn. The camera stays on the places and the objects — the gallery, the island, the vault door — which is also what makes a true-crime short look like a documentary rather than a reconstruction.
03
Your research, kept exactly
The script comes from a language model, and a model can get a date, a number or a name wrong even when told not to. Read every line before you render and check it against a source you trust — or paste your own researched notes with “keep my facts”, and the script keeps them exactly and adds nothing beyond them. For a channel or a podcast with its own research, that is the better way in: a short paragraph of the facts you have checked, the dates and the places, turned into a narrated short that says nothing your notes do not.
Each scene is one cinematic frame generated from its own line — an empty museum gallery at closing time, a prison island in fog, a city street at night in the year it happened. 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. No real person’s face is drawn: the frames show places, buildings, objects, weather and light, never the people in the case, a victim, a weapon in use or blood. Every scene is drawn on its own, so a street or a room will not match exactly from shot to shot, and nobody on screen speaks — the narrator tells the story and there is no lip sync. 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 documentary or retro. 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
True-crime and history channels
A historical case a day for Shorts, TikTok or Reels, in one narrator’s voice and one look, built from facts you have checked.
Podcasters promoting an episode
A one-minute vertical cut of the case your episode covers, made from your own show notes, to post the day the episode goes out.
History and law teachers
A documented case told in a minute on the board, as the opening of a lesson on evidence, investigation or how a famous case was solved.
Writers researching a period
The facts of an old case you are writing about, told back to you as a short, to hear how the story lands before you write your version.
Compared
What this replaces
Six things somebody has to arrange to make one short, and who arranges them.
Input
The usual way: Research the case, write the script, then clear archive photos and footage.
With Veedio: A named historical case, or your own researched notes kept exactly.
Visuals
The usual way: License archive footage per clip, or film reconstructions with actors.
With Veedio: A cinematic frame of the places and objects from each beat’s own line, set in motion.
Voiceover
The usual way: Book a narrator with a documentary voice, and rebook for every correction.
With Veedio: A deep documentary narrator by default, 5 voices to choose from, a corrected 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
Research the case, write the script, then clear archive photos and footage.
A named historical case, or your own researched notes kept exactly.
Visuals
License archive footage per clip, or film reconstructions with actors.
A cinematic frame of the places and objects from each beat’s own line, set in motion.
Voiceover
Book a narrator with a documentary voice, and rebook for every correction.
A deep documentary narrator by default, 5 voices to choose from, a corrected 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.
The script comes from a language model, and a model can get a date, a number or a name wrong even when told not to. Read every line before you render and check it against a source you trust — or paste your own researched notes with “keep my facts”, and the script keeps them exactly and adds nothing beyond them. The brief tells only what is well documented, says where accounts disagree, and invents no date, number, quote, motive or detail.
Which cases can it make a video about?
Historical cases only: the brief tells what court records, official reports and long-established reporting say about a case decades old, says where accounts disagree or where a case was never solved, and invents no date, number, quote, motive or detail. It does not write about a recent case, an open investigation or a living private person, and it names nobody as guilty who was not convicted — in an unsolved case, a theory is told as a theory.
How does it treat victims and their families?
The story is what happened and how it was solved, or why it never was — not the suffering of the people it happened to. Victims are named with respect or not at all, nothing is gory, no injury is described in detail and no death is dramatised. Witnesses, relatives and bystanders who may still be alive are referred to by their role, never by name.
Can it say who did it in an unsolved case?
No. It names nobody as guilty who was not convicted. An unsolved case is told as unsolved, and each theory about it is told as a theory, with the evidence the record gives for it.
Will it show the people involved?
No real person’s face is drawn: the frames show places, buildings, objects, weather and light, never the people in the case, a victim, a weapon in use or blood. Every scene is drawn on its own, so a street or a room will not match exactly from shot to shot, and nobody on screen speaks — the narrator tells the story and there is no lip sync.
Can I use my own research?
Yes, and for a channel that is the better way. Paste the facts you have checked — dates, places, what happened in what order — and say keep my facts. The script keeps them exactly, adds nothing beyond them, and comes back for you to read before anything renders.
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.