Home › OCR — Read Text
OCR — extract text from a photo or scanned PDF
How to use
Choose an image or PDF, pick the language (English, Turkish, TR+EN, German, French, Spanish) and press Read text. The text appears in an editable box; copy it or download a TXT file.
Uses
Quoting from a book page, digitising invoices and receipts, transcribing signs or lecture notes.
Frequently asked questions
Is my image sent anywhere?
No. Recognition runs in your browser with Tesseract.js. Only the language data (about 10 MB) is downloaded on first use; the image never leaves your device.
How can I improve accuracy?
Use a flat, well-lit, high-resolution image; straighten skewed pages first. Handwriting is not supported.
Is there a limit for PDFs?
The first 5 pages of a PDF are read; split longer documents first.