Extract text from images (JPG/PNG/WEBP) and PDF pages — locally in your browser. Drag & drop files, paste with Ctrl +V , pick language(s), then hit Start OCR .
1) Files
Queue: 0
Clear
2) Languages
Choose one or more
English (eng)
Deutsch (deu)
Français (fra)
Español (spa)
Italiano (ita)
Português (por)
Nederlands (nld)
Polski (pol)
Türkçe (tur)
Čeština (ces)
Dansk (dan)
Svenska (swe)
Norsk (nor)
Suomi (fin)
Română (ron)
Magyar (hun)
Русский (rus)
Українська (ukr)
Ελληνικά (ell)
العربية (ara)
עברית (heb)
हिन्दी (hin)
中文(简体) (chi_sim)
日本語 (jpn)
한국어 (kor)
Tip: Fewer languages = faster.
3) Options
Page Segmentation
Auto (no OSD)
Single block of text
Sparse text
Single line
Single word
Render scale (PDF & large images)
Auto (1.0x)
1.5x
2.0x
3.0x
Higher = sharper OCR, slower processing.
▶ Start OCR
■ Cancel
Queue Preview
Images and PDF pages to be recognized. Use Delete to remove a selected item.
Output
Copy text
Save .txt
Characters: 0
Privacy: Files never leave your browser. Uses Tesseract.js + pdf.js (CDN loaded).
