OCR PDF

Turn scans and photos into Word, Excel, a searchable PDF or plain text.

What do you need? Pick a job, or just add a file to see every format.

How it works
  1. 1Pick a job, add a scanChoose a job such as Receipt or invoice to Excel, or skip it. Then add a scanned PDF or a photo of a page, up to 100 MB.
  2. 2Check the recognized textCompare it with the scan. Switch the language and run it again if needed.
  3. 3Download your fileWith a job picked, your file is ready when reading finishes. Or choose any of 9 formats, or all of them in one ZIP.
At a glance
uploaded: text is recognized in your browser
0 bytes
searchable PDF, Word, Excel, Markdown and more
9 formats
receipt to Excel, scan to Word, searchable PDF, photo to text
4 one-step jobs
no sign-up, no page credits
Free

Questions and answers

How do I make a scanned PDF searchable?

Add the scan, let recognition finish, then choose Searchable PDF as the download. You get the original pages with an invisible text layer, so you can search, select and copy.

Is my document uploaded for OCR?

No. Text recognition runs in your browser. The first time, your browser fetches the recognition files from Pagestro, but your document itself never leaves your device.

What do the one-step jobs do?

Each job sets the reading options and the file type for you. Receipt or invoice to Excel gives a spreadsheet with the item table and the labelled fields such as date and total. Scanned contract to Word gives an editable .docx. Make a scan searchable gives your original pages with text you can find and copy. Photo of a page to text gives plain text. Your file is offered as soon as reading finishes, and you can still download any other format.

How accurate is it?

On our own 10 test pages, clean and made to look scanned, the default reading mode read 98.5–100% of characters correctly and found every labelled field on the invoices and the receipt. Those are pages we made ourselves, not a public benchmark; the method and limits are at pagestro.com/ocr/accuracy. Clean printed text is usually recognized well. Handwriting is marked as handwriting and read on a best-effort basis; formulas are kept as plain text, not converted to LaTeX. Low-resolution or skewed scans and decorative fonts lower accuracy, so check the preview before you rely on the result.

Which languages are supported?

English; Multilingual European, which reads French, German, Spanish, Italian and Portuguese together with English; Chinese (Simplified), Japanese and Korean. Recognition starts in English; pick another language and run it again in one click.

Does OCR work on photos and images?

Yes. Besides PDFs you can add JPG, PNG, WebP, BMP and TIFF images. Sharp, straight, evenly lit pages give the most accurate text.

Can I convert a scanned PDF to Word?

Yes. Pick Scanned contract to Word, or choose Word as the format. Headings, paragraphs and detected tables are rebuilt as an editable .docx.

Does it keep the layout?

Yes. Columns, boxes, tables, label and value pairs (like Invoice # and its number) and the reading order are worked out from where things sit on the page. The Layout view shows every block where it was on the scan.

Can I get the text out of Chinese, Japanese or Korean scans?

Yes, in every format, including the searchable PDF: its hidden text layer uses fonts that cover Chinese, Japanese, Korean, accented Latin, Greek and Cyrillic, so that text can be searched and copied.

More free PDF tools

At a glance

uploaded: text is recognized in your browser
0 bytes
searchable PDF, Word, Excel, Markdown and more
9 formats
receipt to Excel, scan to Word, searchable PDF, photo to text
4 one-step jobs
no sign-up, no page credits
Free

Who it’s for

For anyone with paper to turn into text

  • Text is searchableScanned agreement

    Offices and law firms

    Search scanned files

    Make scanned agreements searchable without sending them anywhere.

  • Table exportedExcel and CSV

    Accountants

    Receipts and statements to Excel

    Line items, dates and totals land in a spreadsheet instead of being retyped.

  • Copied to WordHeadings and paragraphs kept

    Students and researchers

    Quote from printouts

    Turn photocopies and photos of pages into text you can cite.

Scans you can’t search or copy

The scan beside its text, ready to use

Check the recognized text against the original page, then save a searchable PDF or an editable Word file.

OCR Studio showing a scanned page next to its recognized, structured text

Retyping tables by hand

Tables come out as tables

Detected tables keep their rows and columns, so they export straight to Excel or CSV.

A table recognized from a scanned invoice, shown as rows and columns in OCR Studio

Sensitive scans on a stranger’s server

Your pages are read on your device

Many OCR sites need your scan on their server. Here your pages are read inside your browser and never sent anywhere. The first scan takes a little longer while your browser fetches the text recognition files from Pagestro.

OCR Studio with a scanned letter loaded and the reading settings, which note that text is read on your device

From scan to text in three steps

  1. 1

    Pick a job, add a scan

    Choose a job such as Receipt or invoice to Excel, or skip it. Then add a scanned PDF or a photo of a page, up to 100 MB.

    OCR PDF start screen: four one-step jobs above a plain file picker
  2. 2

    Check the recognized text

    Compare it with the scan. Switch the language and run it again if needed.

    Recognized text shown next to the original scan
  3. 3

    Download your file

    With a job picked, your file is ready when reading finishes. Or choose any of 9 formats, or all of them in one ZIP.

    Export options for the OCR result

Pricing

Free, and it stays free

Compare every plan

Free

On every plan, including Free. No account needed.

  • OCR and every PDF, image and conversion tool: included
  • Paid plans are for the business tools: more signature requests, sent invoices, dynamic QR codes and short links.

How Pagestro compares

How Pagestro compares
PagestroDesktop softwareUpload-based sites
Document stays on your deviceYesYesNo
Nothing to installYesNoYes
Searchable PDF, Word and Excel from one runYesVariesVaries
PriceFreeOften a paid licenseOften free with limits

OCR PDF questions

Didn't find your answer? Write to us and we'll reply by email.

How do I make a scanned PDF searchable?

Add the scan, let recognition finish, then choose Searchable PDF as the download. You get the original pages with an invisible text layer, so you can search, select and copy.

Is my document uploaded for OCR?

No. Text recognition runs in your browser. The first time, your browser fetches the recognition files from Pagestro, but your document itself never leaves your device.

What do the one-step jobs do?

Each job sets the reading options and the file type for you. Receipt or invoice to Excel gives a spreadsheet with the item table and the labelled fields such as date and total. Scanned contract to Word gives an editable .docx. Make a scan searchable gives your original pages with text you can find and copy. Photo of a page to text gives plain text. Your file is offered as soon as reading finishes, and you can still download any other format.

How accurate is it?

On our own 10 test pages, clean and made to look scanned, the default reading mode read 98.5–100% of characters correctly and found every labelled field on the invoices and the receipt. Those are pages we made ourselves, not a public benchmark; the method and limits are at pagestro.com/ocr/accuracy. Clean printed text is usually recognized well. Handwriting is marked as handwriting and read on a best-effort basis; formulas are kept as plain text, not converted to LaTeX. Low-resolution or skewed scans and decorative fonts lower accuracy, so check the preview before you rely on the result.

Which languages are supported?

English; Multilingual European, which reads French, German, Spanish, Italian and Portuguese together with English; Chinese (Simplified), Japanese and Korean. Recognition starts in English; pick another language and run it again in one click.

Does OCR work on photos and images?

Yes. Besides PDFs you can add JPG, PNG, WebP, BMP and TIFF images. Sharp, straight, evenly lit pages give the most accurate text.

Can I convert a scanned PDF to Word?

Yes. Pick Scanned contract to Word, or choose Word as the format. Headings, paragraphs and detected tables are rebuilt as an editable .docx.

Does it keep the layout?

Yes. Columns, boxes, tables, label and value pairs (like Invoice # and its number) and the reading order are worked out from where things sit on the page. The Layout view shows every block where it was on the scan.

Can I get the text out of Chinese, Japanese or Korean scans?

Yes, in every format, including the searchable PDF: its hidden text layer uses fonts that cover Chinese, Japanese, Korean, accented Latin, Greek and Cyrillic, so that text can be searched and copied.