How to Extract Text from an Image (Free OCR in Hindi, English and 25+ Languages)

Retyping text from a photo, a scanned page or a screenshot is slow and full of mistakes. OCR (Optical Character Recognition) reads the text in an image and turns it into editable text you can copy, paste and search. This guide shows how to extract text from an image for free, including Hindi, Marathi and other Indian languages.

How to convert an image to text

1. Open ImagesLite Image to Text.
2. Choose the language of the text. You can select two, for example English + Hindi.
3. Drop your image or PDF onto the box, or paste a screenshot with Ctrl + V.
4. Wait a few seconds while the text is read. The first run downloads the language data once.
5. Check the result, then click Copy text or Download .txt.

What can you extract text from?

• Screenshots of chats, apps, videos or websites that don’t let you select text
• Photos of printed pages: books, notices, notes and handouts
• Scanned PDFs, where every page is read in turn
• Receipts and invoices: copy totals, dates, GST numbers and addresses
• Business cards and posters: grab phone numbers and emails quickly

Supported languages

The tool recognises more than 25 languages, including English, Hindi, Marathi, Bengali, Tamil, Telugu, Gujarati, Kannada, Malayalam, Punjabi, Urdu, Nepali, Arabic, Chinese, Japanese, Korean, Spanish, French, German, Russian and more. For documents that mix two languages, such as Hindi and English, select both for the best accuracy.

Tips for the most accurate results

• Use a sharp, well-lit image. Blurry or dark photos are the most common cause of errors.
• Photograph the page straight on, not at an angle, and fill the frame with the text.
• Crop away clutter such as pictures, stamps and table edges before running OCR. The Photo Editor can help.
• Pick the right language. Reading Hindi text with only English selected produces gibberish.
• Printed text works best. Neat handwriting can work, but expect to correct some words.

Is it private?

Yes. ImagesLite runs the OCR engine inside your browser, so your images are never uploaded. That makes it suitable for personal documents like letters, forms and IDs.

Related tools

• Have a large scanned PDF? Shrink it with Compress PDF after extracting the text.
• Need just a few pages? Extract them with Split PDF first.
• Copied text has strange bold or fancy characters? Clean it with Remove Unicode Styling.
• Want to turn photos of pages into a document? Use Image to PDF.

Frequently asked questions

How accurate is free OCR?

For clear printed text, accuracy is usually above 95%. Quality of the image matters more than anything else.

Can it keep the original formatting?

OCR extracts plain text and line breaks. Tables, columns and fonts are not preserved, so some tidying may be needed.

Why is the first scan slower?

The recognition engine and language file (a few MB) download on first use and are then cached by your browser.

Extract text from an image now →