Which languages are supported?

Six built-in languages: English, Tamil, Hindi, Telugu, Malayalam and Kannada. The underlying Tesseract engine supports 100+ languages, and more presets can be added on request.

How accurate is the OCR?

Accuracy depends on scan quality. Clean scans at 150 DPI or higher with straight, well-lit text give the best results. The tool shows a confidence score for each run.

What files can I upload?

JPG, PNG, TIFF, WebP and PDF files up to 50 MB. For PDFs, each page is recognised.

What do I get as output?

Recognised plain text you can copy or export as a TXT file — ready to paste into Word, Google Docs or any editor.

Is my document uploaded?

No. Tesseract runs locally in your browser via WebAssembly. Your document never leaves your device.

Which languages are supported?

Six built-in languages: English, Tamil, Hindi, Telugu, Malayalam and Kannada. The underlying Tesseract engine supports 100+ languages, and more presets can be added on request.

How accurate is the OCR?

Accuracy depends on scan quality. Clean scans at 150 DPI or higher with straight, well-lit text give the best results. The tool shows a confidence score for each run.

What files can I upload?

JPG, PNG, TIFF, WebP and PDF files up to 50 MB. For PDFs, each page is recognised.

What do I get as output?

Recognised plain text you can copy or export as a TXT file — ready to paste into Word, Google Docs or any editor.

Is my document uploaded?

No. Tesseract runs locally in your browser via WebAssembly. Your document never leaves your device.

OCR — Extract Text

Extract text from scanned PDFs and images using Tesseract OCR. Supports 6 languages.

Language:

Drop image or PDF here

JPG, PNG, TIFF, WebP, PDF — max 50 MB

Choose File

Supported languages

EnglishEnglish

Tamilதமிழ்

Hindiहिंदी

Teluguతెలుగు

Malayalamമലയാളം

Kannadaಕನ್ನಡ

Tips for best results

Use the scanner Enhanced preset for better contrast.

Ensure text is not skewed more than 5°.

Minimum 150 DPI for reliable recognition.

Avoid shadows across text areas.

How to use OCR — Extract Text

Done in under a minute — right in your browser.

1
Open the OCR tool
Go to yumpdf.com/ocr in any browser.
2
Upload your scan
Select a scanned PDF or image (JPG, PNG, TIFF, WebP).
3
Pick the language
Choose the document language for best accuracy.
4
Copy or export the text
Copy the recognised text or export it as a TXT file.

Frequently asked questions

Open the OCR tool, upload your scanned PDF or image, pick the document language, and click Recognise Text. Copy the result or export it as a TXT file.