Image to Text (OCR)
Extract text from photos, screenshots and scans - English, Hindi and 8 more Indian languages.
Your files stay on this device
or drop them here, or paste with Ctrl+V
JPG, PNG, WEBP, BMP, TIFF, GIF, HEIC, PDF · up to 20 files · stays on your device
How to use Image to Text (OCR)
- 1Add one or more files - drag and drop or tap to choose. Accepted: JPG, PNG, WEBP, BMP, TIFF, GIF, HEIC, PDF.
- 2Adjust the settings if you need to - the defaults suit most people.
- 3Press “Extract text”. Processing happens on your device (the engine downloads once, then is cached).
- 4Download your TXT, one by one or all together as a ZIP.
About this tool
Optical character recognition turns a picture of words into words you can select, search and edit. This tool uses Tesseract, the long-established open source engine, compiled to run inside your browser, so photographs of documents never leave your device. Accuracy depends almost entirely on the image. Sharp, evenly lit, straight-on photographs of printed text are recognized very well, often above 90 percent confidence, and every result shows that score so you know how much checking is needed. Blurry photos, harsh shadows, angled shots and decorative fonts all reduce it, and handwriting is outside what the engine is trained for. Choosing the right language matters as much as image quality: pick English plus Hindi for mixed government documents, and Marathi rather than Hindi for Marathi text, since they share a script but differ in vocabulary. The first run downloads the engine and your language data, a few megabytes, after which it is cached and works offline.
- Accepts
- JPG, PNG, WEBP, BMP, TIFF, GIF, HEIC, PDF
- Gives you
- TXT
- Files at once
- Up to 20
- Processed
- On your device
Frequently asked questions
Which languages are supported?
English, Hindi, Marathi, Gujarati, Bengali, Tamil, Telugu, Kannada, Malayalam and Punjabi, including mixed English and Hindi documents.
Can it read handwriting?
Generally no. Tesseract is trained on printed text. Very neat block capitals sometimes work, but cursive writing does not.
How do I improve accuracy?
Photograph the page flat and square in good light, fill the frame with the text, and choose the correct language. Running the photo through Document Scanner first often lifts the confidence score noticeably.
Can it read handwriting?
Tesseract is trained for printed text. Neat block handwriting sometimes works; cursive usually doesn't.
How do I get the best results?
Use a sharp, well-lit, straight photo where text is at least 20 pixels tall, and choose the correct language.
Is Image to Text (OCR) free?
Yes. There's no sign-up, no watermark and no usage limit.
Are my files uploaded to a server?
No. Image to Text (OCR) runs entirely in your browser. Your files never leave your device and nothing is stored - close the tab and everything is gone.
Which file types can I use?
JPG, PNG, WEBP, BMP, TIFF, GIF, HEIC, PDF. Files are checked by their actual content, not just the extension, so renamed or damaged files are caught early.
Is there a file size limit?
Each file can be up to 200.0 MB, and you can process up to 20 files at once. Because processing uses your device's memory, very large files work best on a computer.
Does it work on my phone?
Yes. It works in modern mobile browsers on Android and iPhone. Heavier jobs (large PDFs, OCR) are faster on a computer.