How to get text from a scanned PDF
Drop your scanned PDF into the box above, or click Choose files.
Choose Word (DOCX) to edit the text, or TXT for plain text, and the language the document is in.
Click Read text. Each page is read in turn; the first time, the language data (2 to 3 MB) is downloaded once.
Check the recognised text below the file, copy it, or download the Word or text file.
Why OCR a scanned PDF?
Contracts, invoices, old letters and pages scanned at an office are usually saved as images inside a PDF. You can read them, but you can't copy a sentence, search for a name or change a word. Converting them to Word normally fails for the same reason: there's no text to convert.
OCR (optical character recognition) recognises the letters in the page images and turns them back into text you can edit, search and paste anywhere.
What you get, and what you don't
The words and line breaks of every page, in reading order, with a page break between pages in Word. Layout, fonts, tables, columns and pictures aren't rebuilt: this is about getting the text back, not an exact copy of the page.
Pages that already have selectable text are read from it directly, which is faster and exact. Clear, straight, well-lit scans read best; handwriting and very small print don't read reliably.
| Tool | Use it for | What you get |
|---|---|---|
| PDF OCR | Scanned PDFs: pictures of pages | The text, as Word or TXT |
| PDF to Word | PDFs with selectable text | Text with layout and tables |
| Image to text | Photos and screenshots of text | The text of one picture |
Is it safe?
Yes. PDF OCR runs entirely in your browser. Your files are read and converted by your own device using built-in browser technology, so they are never uploaded to a server and nobody else can see them.
You can check this yourself: open your browser's developer tools, switch to the Network tab and convert a file. No upload requests are made.
Pages are drawn and read in your browser, so the document never leaves your device. Only the language data is downloaded, from our own server.
Files stay in this tab's memory only until you remove them or close the page.
Frequently Asked Questions
How do I know if my PDF is scanned?
Try to select a word in your PDF viewer. If you can't, or the whole page gets selected as one picture, it's scanned. PDF to Word will also say so.
Which languages are supported?
Turkish and English, including Turkish letters like ç, ğ, ı, ö, ş and ü. Choose the document's language before reading.
Will the Word document look like the original?
It has the same text in the same order, one paragraph per line, but not the original layout, tables or images. Formatting it is up to you.
How long does reading a scan take?
A few seconds per page on a recent computer or phone, so a 10-page scan takes under a minute. Keep the page open until it's done.
Is my document uploaded?
No. Everything happens in your browser, which suits contracts, IDs and other private documents.