HomeAI Detector › AI Document Detector

AI Document Detector — a score for every page, not one for the file.

Upload a PDF up to 10 MB and every page goes through the detector on its own, giving you a page-by-page map of exactly where the AI-looking writing sits plus a document score on top. Word .docx and .txt are accepted too, but they carry no fixed page boundaries, so those return a document score only. The first 3 documents a day need no account and no card. There is no OCR here, so a scanned PDF needs OCR-processing first.

Scan a document free See what per-page means
PDF, DOCX, TXT up to 10 MB PDFs scored page by page No signup to start
The difference

One number hides where the problem is.

A clean introduction followed by three pasted pages averages out to a middling document score, which tells a reviewer nothing they can act on. Scored page by page, the same file stops hiding.

Page 118
Page 224
Page 351
Page 488
Page 591
Page 684
Page 731

Illustration of the output shape. This document averages to a forgettable 52 overall; page by page it points straight at pages 4 to 6. Page 8 is a reference list under 30 words, so it is reported unscored rather than given a number.

Each page is a separate detector call

A PDF is split at its real page boundaries first, then every page is sent through the same classifier independently. Nothing is averaged before scoring, so a spike on one page cannot be diluted by twenty clean ones around it. Pages are processed a few at a time against a bounded budget, which is why a long document returns "scored the first N pages" rather than timing out.

The page map needs a PDF

This is the one honest caveat on the format list. A PDF carries fixed page boundaries, so the map lines up with the pages you can see. A .docx or .txt has no fixed pages — the page breaks you see in Word are produced at render time by your font and margin settings — so those files are accepted and scored, but they return a document score without a page map. If you want the map, export the file to PDF first, which takes one menu click.

Bands, not just numbers

Every scored page returns 0 to 100 with a band attached: 70 and above reads as AI, 40 to 69 as mixed, below 40 as human. The bands exist so a reviewer scanning a 40-page map can find the red pages without reading forty numbers. The underlying score is always shown next to the band.

Near-empty pages say so

Pages under roughly 30 words are reported as unscored rather than given a number. Title pages, reference lists, section dividers and stub final pages give the detector almost nothing to work with, and a confident-looking score on twelve words is noise, not evidence. The page still appears in the map so the count adds up.

How it works

Three steps from file to page map.

No account for the first three documents a day, no extension to install, no copy-paste through a text editor.

1. Drop the file in

Open the document detector and drag a PDF, .docx or .txt onto the upload area, or click to pick it from a folder. The cap is 10 MB per file. The file type is checked by its actual contents rather than its extension, so a spreadsheet renamed to .docx is caught and refused with a message that explains why.

2. Text is pulled out page by page

PDFs are read for their selectable text layer with page boundaries intact, so the page numbers in the result line up with the page numbers in the file you uploaded. Word files are read out of the document XML, which has no fixed pages, so a .docx is scored as one document. Nothing is retyped, reflowed or pasted through an intermediate textarea.

3. Every page is scored on its own

Each page goes through the detector separately and comes back with its own 0 to 100 score and band, alongside a document-level summary. Pages past your tier's scoring cap are still counted and reported in the page total; they simply do not each get an individual score.

What it reads

Accepted, refused, and the honest gaps.

This tool reads prose. Being specific about what it turns away matters more than a long format list, because a refusal with a reason is more useful than a scan that silently returns nothing.

Accepted: PDF, DOCX, TXT

Text-extractable PDFs, Word .docx files, and plain .txt, up to 10 MB each. These cover the overwhelming majority of what actually gets submitted: exported essays and theses, chapters, reports, contracts, proposals, and anything saved out of Word or Google Docs as a PDF or .docx. Only PDFs come back with a page map; .docx and .txt return a document score, because neither format has fixed pages to split on.

Refused by name, with a reason

Spreadsheets (.xlsx, .xls, .csv), slide decks (.pptx, .ppt), legacy .doc, and .pages, .odt, .rtf and .epub are turned away with a message telling you what to do instead, usually exporting to PDF or .docx. Because .docx, .xlsx and .pptx are the same underlying container, a workbook or deck renamed to .docx is caught by inspecting the contents rather than trusting the extension.

No OCR on this tool

A PDF from a flatbed scanner or built from phone photos holds pixels, not characters, and there is no OCR step here. Run the scan through any OCR tool first and upload the searchable PDF it produces. Saying so plainly is better than claiming an OCR layer that does not exist.

Not a bulk tool

The document detector takes one file at a time and returns a page map for it. If you need to queue many documents at once and sort the results by score, that is Bulk Scan on the Business tier, which is a different surface with a different workflow.

Limits

Documents per day, pages per document.

Two separate numbers, and they are worth keeping apart. One is how many files you can scan in a day; the other is how many pages inside each file get their own individual score.

No account: 3 documents a day, first 5 pages scored

Enough to check a real submission before deciding whether the tool is worth an account. This anonymous allowance is shared with the text AI detector, so three document scans and three text scans come out of the same daily pool of three, not six.

Free account: 5 documents a day, 20 pages each

Covers a full essay or a thesis chapter end to end rather than just the opening pages. No card required.

Starter: 25 documents a day, 50 pages each

Sized for a student or a light reviewer working through submissions a few times a week.

Pro and above: 100 documents a day, 100 pages each

Pro scores 100 pages per document and allows 100 documents a day. Business and Enterprise lift the daily document limit while keeping the same 100-page scoring depth per file. The page caps are latency limits rather than billing limits: pages past the cap are still counted and reported, they just are not each scored individually.

Pricing

Pricing for document scanning.

Start with no account at all. Paid tiers billed in USD with yearly billing saving 25%. Full details on the pricing page.

Free
$0/forever

 

Without an account: 3 documents a day, first 5 pages scored.
  • 5 documents / day
  • 20 pages scored per document
  • PDF, DOCX, TXT up to 10 MB
  • No card required
Scan a document
Starter
$7.49/month

Billed $89.88/year, Save $30

For students and light reviewers working through submissions weekly.
  • 25 documents / day
  • 50 pages scored per document
  • 20,000 AI rewriter words/mo
  • Email support
Get Starter
Business
$29.99/month

Billed $359.88/year, Save $120

For teams reviewing submissions at volume across a shared workspace.
  • Unlimited documents / day
  • 100 pages scored per document
  • 150,000 AI rewriter words/mo
  • Five workspace seats
Get Business
Use cases

When a page map beats a single score.

Four situations where knowing which page matters more than knowing the average.

A thesis chapter written over months

Long documents are rarely uniform. A chapter drafted across a semester can be entirely the student's own except for a literature summary pulled from a chatbot in a bad week. A document-level score buries that; the page map puts it on one line.

A submission you have to justify questioning

"The document scored 58" is not a conversation anyone can have. "Pages 4 through 6 scored 84 to 91, the rest sit under 35" is specific enough to open the file and read those pages together. Detectors are not proof, and the page reference is what makes the follow-up conversation about the writing rather than about the tool.

A report or proposal assembled by several people

Multi-author documents are the natural case for per-page scoring, because contributions usually break along section boundaries. The map shows which contributor's section is worth a second look before the document goes out.

A file you would rather not retype

Copy-pasting a 30-page PDF into a text box collapses paragraphs, drags in running headers and page numbers, and takes long enough that most people simply do not bother. Uploading the file keeps the page boundaries the result refers to.

Read this before acting on a score

What this detector cannot tell you.

A per-page map is better evidence than a single number. It is still not proof, and we would rather say so here than have you find out from a bad decision.

A flagged page is a prompt to read, not a verdict

AI detectors work on statistical patterns in writing. Careful, formal, heavily-edited prose can read as machine-generated, and lightly-edited AI output can slip under. The right response to a red page is to open it and read it.

Non-native English carries a known false-positive bias

Writing produced by someone taught English formally as a second language shares measurable surface features with AI-generated text: consistent sentence length, conventional connectives, restrained vocabulary. This is a documented weakness of detectors generally, including this one. Weigh a flagged page against what you know about the writer.

English only

The classifier is trained and calibrated on English. Documents in other languages will return a score, but it is not a number to rely on.

It cannot name a model

The detector reports how AI-like the writing reads. It does not identify which assistant produced it, and any tool claiming to name the specific model from prose alone is overstating what is possible.

How to choose

Five questions to ask any AI document detector.

Most tools in this category accept a file and return one number. These are the questions that separate them, with our own answers stated plainly so you can hold us to the same standard.

1. Does it score the document, or just the first few thousand characters?

Many detectors accept a file upload but then truncate the extracted text to whatever their paste box accepts, scoring only the opening pages while presenting the result as a verdict on the whole document. Ask what happens to page 30. Our answer: pages are scored individually up to your tier's cap of 5, 20, 50 or 100, and pages past the cap are reported as counted-but-unscored rather than quietly dropped.

2. Does it tell you where, or only how much?

A single document percentage cannot be acted on. If a tool says 58% without saying which pages, you still have to read the whole file. Our answer: every scored page carries its own number and band, so the map points at the pages worth opening.

3. What does it do with a near-empty page?

A title page or a reference list has almost no prose in it. A detector that returns a confident score on twelve words is inventing a number. Our answer: anything under roughly 30 words comes back labelled unscored, and it still appears in the page count so the totals add up.

4. Is it honest about scanned files?

Plenty of tools imply that any PDF will work. A scanned PDF holds pixels, not characters, and without an OCR step there is nothing to score. Our answer: there is no OCR here, we say so before you upload, and the fix is to run the file through any OCR tool first.

5. What does it cost to find out if it works?

Free tiers in this category often mean a handful of lifetime uses, or a result hidden behind a signup or a card. Our answer: 3 documents a day with no account, no card and no email, sharing one pool with the text detector. If it is useful you will know before you have given us anything.

The honest trade-off

Where this tool is weaker: no OCR, no bulk queue, no spreadsheet or slide-deck support, and English-only calibration. If you need to sweep two hundred files at once, that is a different surface. If you need one document read properly, page by page, this is built for that.

FAQ

AI document detector frequently asked.

What is an AI document detector?
An AI document detector takes a whole file rather than a block of pasted text and reports how much of it reads as AI-generated. The TextSight document detector accepts PDF, DOCX and TXT up to 10 MB. For a PDF it splits the file at its real page boundaries and runs the detector separately on each page, returning a per-page map plus a document-level score, so you can see which part of a submission is the problem instead of guessing from one number. DOCX and TXT have no fixed pages and return a document score only.
Do I need an account to scan a document?
No. The first 3 documents per day run without signing up, and the first 5 pages of each are scored. That anonymous allowance is shared with the text AI detector, so three document scans and three text scans come out of the same daily pool of three. A free account raises it to 5 documents per day with 20 pages scored per document.
Why score every page instead of the whole document at once?
Because one number for a 30-page submission hides where the AI-looking writing actually sits. A clean introduction followed by three pasted pages averages out to a middling document score, which tells a reviewer nothing actionable. Scored page by page, the same file shows an obvious spike on the three pages that matter. The per-page map is the evidence; the document score is the summary.
Which file formats does the document detector accept?
PDF, Word .docx, and plain .txt, up to 10 MB per file. Page-by-page scoring needs a PDF, because .docx and .txt carry no fixed page boundaries and so return a document score only. Spreadsheets (.xlsx, .xls, .csv), slide decks (.pptx, .ppt), legacy .doc, and .pages, .odt, .rtf and .epub files are refused by name with a message explaining why rather than failing silently. This tool reads prose, so a spreadsheet renamed to .docx is detected and refused too.
How many pages get scored on each plan?
On a PDF, page scoring covers the first 5 pages without an account, 20 pages on a free account, 50 on Starter, and 100 on Pro, Business and Enterprise. These are latency caps rather than billing caps: pages past the cap are still counted and reported in the page count, they just do not each get their own individual score, and the document still gets its overall score.
Does it work on scanned PDFs?
No. A PDF produced by a flatbed scanner or built from phone photos contains pixels rather than characters, and this tool has no OCR step. It reads the selectable text layer that almost every exported PDF carries. If your file is a scan, run it through any OCR tool first and upload the resulting searchable PDF.
What happens to pages that are nearly empty?
Pages under roughly 30 words are reported as unscored rather than given a number. Title pages, reference lists, section dividers and stub final pages give a detector almost nothing to work with, and a confident-looking score on twelve words is noise rather than evidence. The page still appears in the map, labelled as unscored, so the count always adds up.
How should I read the per-page scores?
Each scored page returns a 0 to 100 AI score with a band: 70 and above reads as AI, 40 to 69 as mixed, and below 40 as human. Treat a single flagged page as a prompt to read that page rather than as proof. AI detectors carry a known false-positive bias against formally-taught and non-native English, so the honest use is to open the flagged page and judge the writing, not to act on the number alone.
Related

More document and file guides.

Further reading

Scan a document. See every page.

PDF, DOCX or TXT up to 10 MB. A score for each page, not one number for the file. First three a day need no account and no card.

Scan a document free See pricing
PDF, DOCX, TXT · Scored page by page · No signup to start