Create your video now·render in about a minute·no watermark on any plan
PDF to Video Generator
Upload a PDF in the composer, or paste a section of it here, and get a narrated, captioned short that explains the document’s main point in plain words.
01Upload the PDF, or paste a section. In the composer, Upload a PDF on the Link tab takes a file of up to 15 MB. Here, paste the summary or the section you want explained.
02Read the script. It comes back one line per scene, held to the document’s words. Check every figure and every recommendation before any picture is made.
03Render it and share it. A vertical short to post to TikTok, Reels or Shorts from the app, or switch to landscape in the composer and download the MP4 for a deck or a course page.
Voice:
Sarah
Captions:
Boxed
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
Executive summary. Many mid-sized manufacturers still sche…
Style: 3D render
Voice: Sarah
Captions: Boxed
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
“Executive summary. Many mid-sized manufacturers still schedule maintenance by the calendar: every machine is serviced on a fixed date whether it needs it or not. This paper sets out an alternative, condition-based maintenance, in which sensors on each machine report vibration and temperature and a service is booked only when the readings drift. It explains what to measure first, how to pilot it on one line, and what to change in the maintenance team’s week.”
Plus this page’s brief, verbatim
The text below comes from a PDF the user has — a whitepaper, a report, a guide, a workbook, a care sheet or a one-pager. Explain its main point as a short narrated video for someone who will never open the document: open on the problem or question the document answers, then its key points in plain words, one per scene, ending on what it tells the reader to do. Use ONLY what the text says: add no fact, number, name, date, source, price or claim that is not in it, do not cite page numbers, and if something is unclear, leave it out. Spell out an acronym only where the text spells it out. If the text is only a web address or a file name with no words from it, do not guess what it says: say only what the address or name itself makes certain (the site's name), and nothing about what it offers. Each scene describes one frame that shows the idea in its line — a workshop floor, a kitchen, a house, a person at a desk — with no text, numbers, charts, tables, logos, document pages or writing in the frame and no one 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
The PDF nobody opens, explained in a minute
Whitepapers, buyer’s guides, workbooks and care sheets are written to be read, and many of the people they are meant for never open them. A short video is how the main point reaches those people: the problem the document answers, the few things it says to do, and where to get the rest. The brief here writes exactly that, for someone who has not read a page of it.
It makes a new narrated video from the document’s words. It is not a slideshow of the PDF’s pages: no page, table, chart or diagram from the file appears on screen, and nothing in the frames is lettered. The page starts on the composer’s 3D render look, vertical, with a reassuring narrator and boxed captions that stay readable over any frame. 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.
02
Uploading the PDF, and what is read from it
On the composer’s Link tab, Upload a PDF takes a file of up to 15 MB, and a PDF at a public link can be pasted there instead. An uploaded file is stored under an unguessable link rather than behind a password: anyone who has that link can open it, so leave out anything confidential. On the Link tab this page’s own brief steps aside: the script writer is given the source itself and told to use only what it says. The look, the voice, the captions and the music this page starts on stay as they are.
Only the PDF’s text layer is read. A scan — pictures of pages — has almost no readable text and is refused with that reason, as is a file that is not really a PDF; paste the text instead. Tables are read as runs of words, and charts, diagrams and photos are not read at all. Of a long document the script writer reads the opening, so for one section of a long report, paste that section or upload it as a PDF of its own.
03
Figures, claims and what to check before it renders
The script is written from the words you give it and told to use only what they say: no fact, figure, price, name, quote or claim that is not in your text. It is still a language model, so read the script before any picture is made: the box here shows it one line per scene, and in the composer, Show me the script first holds the visuals until you approve it. A document is often where the numbers live — a result, a price, a deadline, a measurement — and a figure misread out loud is worse than no figure, so check each one in the script against the page it came from.
Each scene is one generated frame made from its own line of the script, so the video is a sequence of independent pictures joined by cuts, not one continuous shot. On a paid plan each frame is set in motion by default with a short camera move (138 credits for a five-scene video), or choose Stills in the composer and the same video is 13 credits, as pictures with a slow pan. Or switch the composer to Stock footage: real Pexels clips matched to each line, on every plan, which suits a subject that exists — a street, a kitchen, a handshake — better than an idea.
The whitepaper, report or one-pager behind a form, as a short that tells people what is inside before they download it.
Coaches and course creators
A workbook chapter or a worksheet, as a short that explains the exercise in your own words.
Real estate agents
Your buyer’s or seller’s guide, one section per short, posted between listings.
Shop owners
A care sheet, a size guide or the instructions in the box, as a short for customers who will not read the leaflet.
Compared
What this replaces
Six things somebody has to arrange to make one short, and who arranges them.
Input
The usual way: Read the whole document, then write a script that explains it.
With Veedio: Upload the PDF on the composer’s Link tab, or paste the section here.
Visuals
The usual way: The PDF’s pages as slides, with text nobody can read on a phone.
With Veedio: A frame generated from each line, or real stock clips, with no page shown.
Voiceover
The usual way: Somebody on the team records it, then records it again.
With Veedio: A reassuring narrator by default, 20 voices to choose from, a changed line re-read on its own.
Captions
The usual way: Typed in by hand, or left off.
With Veedio: Boxed captions from the approved script, readable over any frame.
Turnaround
The usual way: Days, because the document has to be read before anyone can write.
With Veedio: The document read and the script written in moments, the video right after it.
Changing it
The usual way: The guide is revised and the video has to be made again from scratch.
With Veedio: Paste the revised section or upload the new PDF, then render again.
The usual way
With Veedio
Input
Read the whole document, then write a script that explains it.
Upload the PDF on the composer’s Link tab, or paste the section here.
Visuals
The PDF’s pages as slides, with text nobody can read on a phone.
A frame generated from each line, or real stock clips, with no page shown.
Voiceover
Somebody on the team records it, then records it again.
A reassuring narrator by default, 20 voices to choose from, a changed line re-read on its own.
Captions
Typed in by hand, or left off.
Boxed captions from the approved script, readable over any frame.
Turnaround
Days, because the document has to be read before anyone can write.
The document read and the script written in moments, the video right after it.
Changing it
The guide is revised and the video has to be made again from scratch.
Paste the revised section or upload the new PDF, then render again.
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.
Hand the composer a link to an article, a product page, a YouTube video or a PDF, or paste the page’s text here, and get a new narrated short written only from what the page says.
Type a task, a checklist or a customer situation and get a short narrated training video — one step per scene, captions on every word, ready for a phone or a break-room screen.
Type a topic and an age or level, or paste your lesson notes, and get a narrated educational video that teaches one idea in plain steps, each step drawn and captioned.
Paste the part of a YouTube video’s transcript with the point you want, or hand the composer the video’s link, and get a new narrated, captioned vertical short written only from what the video says.
Yes, in the composer. On the composer’s Link tab, Upload a PDF takes a file of up to 15 MB, and a PDF at a public link can be pasted there instead. An uploaded file is stored under an unguessable link rather than behind a password: anyone who has that link can open it, so leave out anything confidential. The box on this page takes pasted text only, up to 1,200 characters.
Why was my PDF refused?
Usually because it is a scan. Only the PDF’s text layer is read. A scan — pictures of pages — has almost no readable text and is refused with that reason, as is a file that is not really a PDF; paste the text instead. Tables are read as runs of words, and charts, diagrams and photos are not read at all. Of a long document the script writer reads the opening, so for one section of a long report, paste that section or upload it as a PDF of its own. A file over 15 MB is refused too.
Will it read the tables, charts and images in my PDF?
No. Only the text layer is read: a table comes through as a run of words, and a chart, a diagram or a photo is not read at all. If a figure from a chart matters, type it into the text you paste, and check it in the script before it renders.
Does it turn my PDF’s pages into a slideshow?
No. It writes a new narrated video from the document’s words, and no page of the file appears on screen. Each scene is one generated frame made from its own line of the script, so the video is a sequence of independent pictures joined by cuts, not one continuous shot. On a paid plan each frame is set in motion by default with a short camera move (138 credits for a five-scene video), or choose Stills in the composer and the same video is 13 credits, as pictures with a slow pan.
Will it add facts the document does not have?
The script is written from the words you give it and told to use only what they say: no fact, figure, price, name, quote or claim that is not in your text. It is still a language model, so read the script before any picture is made: the box here shows it one line per scene, and in the composer, Show me the script first holds the visuals until you approve it.
Is my document kept private?
Not behind a password. On the composer’s Link tab, Upload a PDF takes a file of up to 15 MB, and a PDF at a public link can be pasted there instead. An uploaded file is stored under an unguessable link rather than behind a password: anyone who has that link can open it, so leave out anything confidential. Pasting only the section you want explained keeps the rest of the document out of it.
Can the video be in a different language from the document?
Yes. Pick the language in the composer and the script is written and narrated in it. There are 20 stock voices, most of them recorded in American English, with 4 British and 1 Australian among them. There is no Irish voice, and voice cloning — your own voice — is on Pro and Studio only. 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 an English-speaker's accent, so listen to the first one before you post a series.
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 138. 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 1 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. 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.
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.