OCR PDF & Image

How it works

1
Upload a scanned PDF or an image (JPG, PNG, WebP, TIFF).
2
Pick the document language — 15+ languages supported.
3
Extract the text, copy it, download it as a .txt file, or save it to your dashboard.

Where does OCR run?+

On your device. Tesseract.js runs in a Web Worker in your browser, so scanned documents never leave your computer.

Which languages are supported?+

English, Spanish, French, German, Italian, Portuguese, Dutch, Russian, Turkish, Arabic, Hindi, Chinese (Simplified), Japanese, Korean, and more.

My PDF is image-based — will this work?+

Yes. For PDFs, each page is rendered and recognized automatically. Use this tool before AI Summary or Translation on scanned documents.

1
Upload a scanned PDF or an image (JPG, PNG, WebP, TIFF).
2
Pick the document language — 15+ languages supported.
3
Extract the text, copy it, download it as a .txt file, or save it to your dashboard.

Where does OCR run?+

On your device. Tesseract.js runs in a Web Worker in your browser, so scanned documents never leave your computer.

Which languages are supported?+

English, Spanish, French, German, Italian, Portuguese, Dutch, Russian, Turkish, Arabic, Hindi, Chinese (Simplified), Japanese, Korean, and more.

My PDF is image-based — will this work?+

Yes. For PDFs, each page is rendered and recognized automatically. Use this tool before AI Summary or Translation on scanned documents.