Skip to content
Folmixo
JPGPNGWebPPDFTXT

Recognize text (OCR)

Text from scans and photos — Russian and English. Recognition runs on your device.

Your files are processed on your device and never uploaded to a server.

Loading tool…

How it works

  1. 1Add a photo, scan or PDF.
  2. 2Choose the language of the text.
  3. 3Click “Recognize text” and download the text.

Limitations

  • The first run downloads the recognition module (about 9 MB) — after that it’s loaded from your browser’s cache.
  • Recognition runs on your device and can take a while: roughly a few seconds per page.
  • Clear scans at 200 dpi or higher work best; handwriting isn’t recognized.

FAQ

Are my files uploaded to a server?
No. Files are processed right in your browser on your device and are never sent anywhere — so it’s safe to convert confidential documents too.
Is it free? Do I need to sign up?
Yes, it’s free and no watermark is added to the result. Without an account you get 20 runs a day; a free account removes the limit.
How do I extract text from a photo or image?
Add a photo, screenshot or scan, choose the language and click “Recognize text”. Copy the text or download it as a .txt file.
Which languages are supported?
English, Russian, or both at once — handy for documents that mix the two.
Can I extract text from a multi-page PDF?
Yes. Choose all pages or only some, for example 1–3, 5. Each page takes a few seconds, and everything happens on your device.
Does it recognize handwriting?
No, printed text only. Sharp scans at 200 dpi or more and photos without glare or strong tilt work best.
Why are there mistakes in the text?
Usually it’s small print, glare, tilt or blur, less often the wrong language setting. For a paper document, capture it with the “Document scanner” first: it straightens the page and whitens the paper, and you can then recognize the resulting PDF here.
Can I extract text from a screenshot or several photos at once?
Yes. PNG screenshots are recognized especially well — they have no glare or tilt. With a free account you can add several images — the text of each appears in one result under its file name.
Are lines and paragraphs kept?
Yes, line breaks and paragraphs are kept. Tables are recognized row by row as plain text — without the grid or cells.
How is this different from “PDF to text”?
“PDF to text” pulls out the text layer a document already has — instantly and without mistakes. Recognition is for scans and photos, where the text is just a picture.

Guide

Other tools