Image to Text (OCR)
Copy the text out of a photo, screenshot or scanned PDF — including Nepali.
Choose photos, screenshots or scanned PDFs
JPG, PNG, WebP, GIF, BMP, PDF · up to 50.00 MB each
or drop them here
Processed in your browser. Your files are not uploaded.
Share this app
Know someone who needs this? Send them straight to it — the link opens this exact tool.
Download the share imageFor Instagram, TikTok or a status, where links do not show a preview.

About this tool
Turn pictures of text into text you can edit and copy: photos of documents, screenshots, receipts, scanned PDFs. It uses Tesseract's neural-network text recogniser, running on your device, in English, Spanish, French, German, Portuguese, Hindi, Nepali and Arabic — up to three at once for mixed text. PDF pages that already contain real text are copied exactly instead of being recognised. Nothing is uploaded; the recogniser itself is served from this site.
How to use Image to Text (OCR)
- Choose one or more photos, screenshots or scanned PDFs.
- Pick the language of the text — two or three for mixed text.
- Press Extract text. The first run downloads the recogniser from this site, then it is fast.
- Correct anything it misread, then copy the text or download it as a .txt file.
Questions
How accurate is it?
Very good on clear, straight, well-lit text — screenshots and scans especially. Photos taken at an angle, handwriting, small or decorative fonts reduce accuracy. Always check names and numbers.
Does it read Nepali?
Yes — choose Nepali (and English too if the text mixes both).
Are my images uploaded?
No. The recogniser runs in your browser. Only the recogniser itself is downloaded, from this site, the first time you use it.
Can it read handwriting?
Neatly printed handwriting sometimes works; joined-up handwriting usually does not. It is built for printed text.
More free apps
All apps →Do this at scale with AI
This app handles the one-off job. These tools handle it as part of a real workflow.