Videos
Turn a PDF into a video
PDFs are read differently here from other files, and the difference is worth knowing. Rather than pulling out the text layer, every page is rendered to an image at roughly 200 dots per inch and looked at. A scan and a digitally exported file therefore go through exactly the same path.
Pages become pictures
The file is rendered page by page at scale 2, which is about 200 DPI, and those page images are what get analysed. Nothing depends on a text layer existing, so a scanned brochure, a photographed page and a clean export all behave the same way. The analysis returns what kind of document it is, a short summary, the language and the key points, and it is told to base every answer only on what the document actually contains.
The page ceiling
Up to 100 pages are rendered and read in one pass, which is the practical ceiling of a single request. Beyond that, the analysis is marked truncated and the later pages simply are not seen. For a video brief this is almost never the binding constraint, because the summary that reaches the director is a few sentences long regardless of whether the source was two pages or eighty.
A PDF is a context source, not a storyboard
This is the expectation to reset. The pages of your PDF do not become the scenes of your video. Its layout, its charts and its images are not lifted out and reused. What crosses over is the meaning: a summary and a list of key points that inform the script. If you want a page from the PDF to appear on screen, export it as a PNG and upload it as an image instead, which is a separate slot with a limit of eight.
When a PDF is the wrong input
Two cases. If the PDF is mostly a design, a poster or a flyer, the analysis will describe it as a design rather than mining its message, which is rarely what you want for a video script. And if the PDF is a form with empty fields, there is nothing there to summarise into an argument. In both cases writing the brief yourself is faster and better.
How it works, in three steps
Step 1
Attach the PDF alongside a real brief
The file supplies the substance, the brief supplies the intent. A PDF with no instructions produces a video about the whole document rather than the part you care about.
Step 2
Export any page you want on screen
Save it as a PNG and add it to the image uploads. Documents are read for context and never displayed.
Step 3
Read the script against the source
Open each scene's narration and check it against the PDF. A summary is a lossy step, and this is where you catch what it lost.
The full walkthrough with screenshots is in the guide Make a promo video with AI voiceover.
Limits worth knowing
- The document upload accepts PDF and plain text only. Word, Excel and PowerPoint are not offered here.
- 100 pages is the ceiling for one analysis. Longer files are read only to that point and marked truncated.
- Nothing from the PDF appears in the video. It informs the writing and is never shown.
- Five documents per generation, and their combined context is capped at 20,000 characters.
Questions people ask
Does a scanned PDF work?
Yes, and about as well as an exported one, because both are read as page images rather than as a text layer. Legibility is what matters, so a sharp scan reads better than a crooked phone photograph of a page.
Can I turn a slide deck PDF into a video?
It will summarise the deck and write a video about it, but the slides will not become scenes. If you want the slides on screen, export them as images and upload up to eight of them.
Will the charts in my PDF be recreated?
Not automatically. Chart scenes take comma separated numbers, so if you want a chart in the video, put the actual figures in the brief and the director can build one.
Is a big PDF slow?
Rendering many pages takes time, and generation is a background job polled for up to sixteen minutes, so there is headroom. If you only care about three pages, extract those three into their own file first.
Make your own video
The button opens the generator with this use case already described. Change the wording to match yours, generate, then edit anything you like.
Create a video with OneCraftRelated pages
Turn a one line idea into a video
A single sentence is a legitimate input, and it is worth knowing exactly how much is being invented on your behalf when you use one. The answer is: the arc, the scene roles, every word on screen, every spoken line, the voice, the tone and often the format as well.
Turn a document into a video
There is an honest thing to say up front. A document you attach here is not transcribed into the video. It is read and summarised into a short description plus a list of key points, and it is that summary the director works from when it plans scenes and writes the script.
Turn images into a video
Upload eight pictures and eight different decisions get made. Some become scenes. Some are grouped so they play together in one. Some are judged to be references you uploaded to explain the video rather than to appear in it, and those are read for their content and then deliberately kept off screen.
More finished work of this kind is on the video examples hub.