OCR: extract text from scanned PDFs and images
Recognize text in scanned PDFs and images.
How it works
- 1
Drop a scanned PDF or an image.
- 2
Choose the language of the document.
- 3
Copy the text or download a .txt file.
Turn scanned documents, photos and screenshots into real, copyable text. Supports English, Chinese and many other languages. Recognition runs in your browser, so your documents are never uploaded.
OCR (optical character recognition) converts pictures of text into real characters. Use it for scanned contracts, photographed pages, receipts and screenshots, then copy, search, translate or edit the text. Pro includes it with no extra fees.
What people use it for
- Extract text from scanned contracts and receipts.
- Digitise printed pages and book scans.
- Make photographed documents copyable.
Tips for best results
- Choose the document language for best accuracy.
- Scan at 200 to 300 DPI with straight pages.
- Use Searchable PDF to keep the original look and add a text layer.
Your files never leave your device
Unlike most online PDF tools, Intelli File does not upload your documents to a server. Everything runs in your browser using your own device, so contracts, IDs and financial records stay private. Only a small usage counter is sent so we can apply daily limits.
Read how we handle privacyWhat to do next
After this, you may want to Searchable PDF, PDF to Word, or Compare PDF.
Frequently asked questions
Is my document uploaded for recognition?+
No. The recognition engine runs in your browser. Only the engine and language data (about 10 MB) are downloaded the first time.
How accurate is it?+
Clean, upright scans of printed text work best. Choose the correct language and use a scan of at least 200 DPI for the best results.
Which languages are supported?+
English, Simplified and Traditional Chinese, Spanish, French, German, Italian, Portuguese, Japanese, Korean and Russian.
How many pages can I process?+
Up to 150 pages per run. Split bigger files first.