Guide
How to extract text from an image
- 1
Add one or more images that contain text.
- 2
Choose the language, and optionally select just the area you want read.
- 3
Extract, check and edit the text, then copy it or download .txt or a searchable PDF.
Features
What Image to Text (OCR) can do
- Powered by the open-source Tesseract OCR engine.
- 18 languages including English, Hindi, Bengali, Tamil, Arabic, Chinese and Japanese, with a second language for mixed documents.
- Automatic clean-up for accuracy: tilted photos are straightened, shadows evened out, table lines and icons removed, and small text enlarged.
- Select area: draw a box to read only the text you want and skip logos, headers or other text.
- A confidence score for every image, with a warning when words were hard to read.
- Keep line breaks as in the image or join them into paragraphs; edit, copy, or download a .txt file or a searchable PDF.
Supported formats and limits
- Input
- JPG, PNG, WebP, HEIC, BMP, GIF
- Output
- Text (TXT, searchable PDF)
- Limits
- Images up to 25 MB each, up to 10 at a time. Printed text works best; handwriting is not reliably recognised. The first use downloads the engine and language data (about 4 MB plus 1–3 MB per language) from this site.
Image to Text (OCR) FAQ
No. The OCR engine (Tesseract) runs inside your browser. The engine and language data are downloaded from EasyFile24 the first time you use them and then cached; your images and the extracted text never leave your device.
For clear, straight photos and scans of printed text, accuracy is usually very high. Each result shows a confidence score and warns you when words were hard to read. Handwriting, blurry or angled photos and decorative fonts are less reliable, so always check the text.
English, Hindi, Bengali, Tamil, Telugu, Marathi, Gujarati, Punjabi, Urdu, Spanish, French, German, Portuguese, Italian, Russian, Arabic, Chinese (Simplified) and Japanese. You can combine two languages for mixed documents.
A PDF that shows your original image but also contains an invisible text layer, so you can search, select and copy the text in any PDF reader.
Choose the correct language and use a sharp photo. Slightly tilted photos, shadows, table borders and icons are handled automatically, and small text is enlarged. To read only part of an image (for example skipping a logo or header), use Select area and draw a box around the text you want.
By default the text keeps the line breaks from the image. Switch the result to Paragraphs to join lines into flowing text, which also repairs words split with a hyphen.
Guides
- How to Copy Text From an Image or a PDFGet editable text out of photos, screenshots, scans and PDFs. Learn when OCR is needed, how to get accurate results, and how to clean up the text afterwards.
- How to Scan Documents to PDF With Your PhoneTurn paper documents into clean, readable PDFs with your phone: photograph the pages, combine them into one PDF, fix rotation, shrink the file and make it searchable.
Related tools
Image CompressorCompress JPG, PNG and WebP images with a live before/after size comparison.IMGJPG to PDFConvert JPG images to PDF. Combine multiple photos, reorder them and choose page size.IMGPDFWord CounterCount words, characters, sentences and paragraphs instantly, with reading time and top keywords.
