How to use the Image to Text (OCR) tool
- Add your imageDrop one or more images, click to choose them, or press Ctrl + V to paste a screenshot.
- Choose the languagePick the language of the text. English words mixed into other languages are detected too.
- Wait a momentThe first run downloads the OCR engine and language data once; after that it is much faster.
- Copy or downloadEdit the extracted text if needed, then copy it or download it as a .txt file.
Features
- 35 languagesIncluding English, Hindi, Bengali, Tamil, Telugu, Marathi, Urdu, Arabic, Chinese, Japanese, Spanish and French.
- Screenshots and photosWorks with screenshots, scanned pages, photos of documents, receipts, book pages and slides.
- Batch OCRAdd many images at once. Each one gets its own editable result, and you can copy or download everything together.
- Smart cleanupSmall images are upscaled for better accuracy, extra blank lines are removed, and lines can be joined into paragraphs.
- Private by designRecognition happens on your device. Your images are not uploaded to a server.
What is OCR?
OCR (optical character recognition) turns a picture of text into real, editable text. A photo of a printed page, a scanned letter or a screenshot only contains pixels, so you can’t search it, copy from it or paste it into a document. OCR looks for the shapes of letters and words and rebuilds the text so you can use it anywhere.
This tool uses Tesseract, the open-source OCR engine originally developed at HP and later maintained with Google’s support, running directly in your web browser.
Common uses
- Copy text from a screenshot of an app, video, error message or social media post.
- Digitize printed documents such as letters, notices and book pages, instead of retyping them.
- Extract details from receipts and invoices for expenses and accounting.
- Grab text from slides or whiteboards photographed during a class or meeting.
- Make notes searchable by turning photos of printed material into text you can search and edit.
Tips for the best accuracy
| Do | Why it helps |
|---|---|
| Use a sharp, well-lit photo taken straight on | Blur, shadows and tilted pages are the main causes of OCR errors. |
| Crop to the text you need | Pictures, logos and backgrounds can confuse the engine. Use Crop Image first. |
| Pick the right language | Each language has its own alphabet and dictionary. Hindi text needs “Hindi”, not English. |
| Prefer printed text | Clear printed and typed text works best. Handwriting is recognized only when it is very neat. |
| Rotate sideways images | Text should be upright. Use Rotate Image if needed. |
Can I OCR a scanned PDF?
Yes, in two steps. First convert the PDF pages to images with PDF to JPG, then drop those images here. If your PDF already contains selectable text (for example, one exported from Word), you don’t need OCR at all; use PDF to Text instead, which is faster and exact.
Is it private?
Yes. The OCR engine and the language files are downloaded to your browser the first time you use a language and then cached, but your images are processed locally and never sent to a server. That makes it safe for ID cards, bank documents and private messages.