About the PDF OCR
Tezmy's PDF OCR tool reads the text in scanned PDFs and photos of documents, the kind of file where you can't select or copy anything because every page is a picture. It uses optical character recognition (OCR) to turn those pictures into real text that you can edit, copy or download as a .txt file. Choose the document's language (English, Spanish, French, German, Portuguese, Italian, Hindi or Arabic) and read all pages or just some. Everything runs in your browser, so your documents are never uploaded.
Updated October 2026
How to use the PDF OCR
- 1Click Select file and pick a scanned PDF or a photo (JPG, PNG or WebP).
- 2Choose the language of the document (up to 3).
- 3For a PDF, read all pages or choose some.
- 4Click Read text and wait while each page is read.
- 5Check and edit the text, then copy it or download it as .txt.
When you need OCR
If you can already select text in the PDF, you don't need OCR: PDF to Text copies it exactly and instantly. The tool tells you when a PDF already contains text.
- A scanned contract, letter or form where you can't select any text.
- A photo of a receipt, notice or page from a book you want to quote.
- Old paperwork scanned as PDF that you want to search or reuse.
- Documents sent as pictures, where retyping everything would take ages.
Choosing languages and pages
Pick the language the document is written in. The reader uses it to recognise letters and accents, like é, ñ and ß, and whole words, so the right choice noticeably improves the result. If a document mixes languages, choose up to three; choosing languages that aren't in the document can make it slightly worse.
For long PDFs, read only the pages you need by choosing Choose and typing pages such as 1-3, 7. Each page takes a few seconds; you can follow the progress and press Stop at any time.
Tips for better results
- Scan at 300 DPI if you can, or photograph the page flat, straight on and in good light.
- Crop photos to the page and rotate them upright first (Crop Image and Rotate Image help).
- Dark text on a plain light background works best; coloured backgrounds and stamps can confuse the reader.
- Check numbers, names and amounts carefully: letters like O and 0, or l and 1, are the most common mix-ups.
- Very small print reads better from a closer photo or a higher-resolution scan.
How it works and what's downloaded
The tool uses Tesseract, a well-known open-source OCR engine, in a version made for web browsers (tesseract.js). Each PDF page is drawn at about 300 DPI and then read. The first time, the engine (about 4 MB) and the language data you need (up to 3 MB per language) are downloaded from our own site and saved in your browser. Your files themselves are never sent anywhere.
Phone or computer
PDF OCR works in any modern browser on Windows, Mac, iPhone, Android and Chromebook. OCR takes a lot of processing, so a computer is faster for long documents; on a phone, reading a few pages at a time works well. Keep the tab open while it reads. After the text is read, scan a single page as a picture with PDF to JPG, or fix a sideways scan first using Rotate & Flip Image.
Features
- Scanned PDFs and photos of documents
- 8 languages, up to 3 in one document
- All pages or chosen pages
- Edit the text before copying
- Copy or download as .txt
- Private: files never leave your device
Frequently asked questions
What is OCR?
OCR (optical character recognition) is software that looks at a picture of text, such as a scan or photo, and works out which letters and words are in it. The result is text you can select, edit, search and copy.
How do I get text from a scanned PDF?
Select the PDF, pick its language and click Read text. Each page is read in turn, and the text appears in a box where you can correct it, copy it or download it as a .txt file.
How accurate is it?
Clear scans of printed text usually come out very well. Accuracy drops with blurry or dark photos, tiny print, unusual fonts, pages that are skewed or upside down, and complicated layouts. Handwriting is generally not recognised well. Always read the result through before relying on it.
Which languages are supported?
English, Spanish, French, German, Portuguese, Italian, Hindi and Arabic. Choose up to three at once for documents that mix languages, for example English and French. Choosing only the languages that are really in the document gives the best result.
Why does the first run take longer?
The first time, your browser downloads the text reader (about 4 MB) and the data for each language you choose (up to 3 MB each) from our site. They're saved in your browser, so the next time it starts much faster.
Does it keep the layout, tables and formatting?
No. You get plain text: the words in reading order, line by line. Columns, tables, fonts and pictures aren't kept. For documents that must look the same, keep the PDF and copy just the parts you need.
Can it make a searchable PDF?
Not at the moment. This tool gives you the text itself, to copy or save as a .txt file. If your PDF already has selectable text, PDF to Text copies it instantly without OCR.
Are my files uploaded?
No. Pages are drawn and read inside your browser. Only the text reader and language data are downloaded from our site; your documents stay on your device.