PDF OCR
Extract Bengali or English text from scanned PDFs. Copy it, download a text file, or make a searchable PDF — all in your browser.
Runs in your browser · Files never uploaded
Make a scanned PDF searchable
Extract Bengali or English text, copy it, save it as a text file, or add a searchable text layer to a PDF copy.
Drop a PDF here · Up to 100 MB and 100 pages
The PDF stays on your device. The OCR engine and language data are bundled with this tool.
How to use PDF OCR
- 1
Choose a scanned PDF
Select a PDF with up to 100 pages. The document is opened in your browser and never uploaded.
- 2
Select the text language
Choose Bengali, English, or both for a mixed-language document.
- 3
Extract the text
Pages are processed one at a time. Follow progress and review the recognized text page by page.
- 4
Copy or download
Copy the result, download a .txt file, or create a searchable PDF copy with an invisible text layer.
Private OCR for Bengali and English PDFs
This tool uses OCR to read text from scanned pages that are stored as images. It can also extract text already present in a regular PDF. The PDF is processed in your browser; only the OCR engine and language data are included as site assets.
Searchable PDF: When you download a searchable copy, an invisible Unicode text layer is placed over OCR-read words. The original page artwork remains in the PDF, while the text can be found and selected in compatible PDF readers.
Recognition depends on scan sharpness, contrast, page angle, and the language chosen. Review important details such as names, dates, and account numbers against the original scan.
Large files: Pages are rendered sequentially with a pixel limit to control memory use. PDFs with more than 100 pages or over 100 MB need to be split or reduced first.