Image to Text Converter (OCR)

Turn pictures into editable text. Upload or paste an image, screenshot, photo or scanned PDF, and this free OCR (optical character recognition) tool extracts the text in seconds. It supports 30 languages, including English, German, French, Spanish, Italian, Hindi, Arabic, Russian, Chinese and Japanese, and handles several images at once. Copy the result, download it as a text file, or create a searchable PDF. Recognition runs on your own device, so your images are never uploaded.

  • 100% free
  • No sign-up
  • Private & local
  • Works on mobile
Drop images or a scanned PDF hereor browse files · PNG, JPG, WebP, BMP, GIF or PDF · paste a screenshot with Ctrl+V · up to 20 files

Private by design: your files are processed locally in your browser and are never uploaded to any server.

What Is OCR?

OCR (optical character recognition) is technology that recognises letters and numbers in an image and turns them into real, editable text. A photo of a document, a screenshot, a scanned page or a picture of a sign contains only pixels: you can't search it, copy from it or edit it. OCR reads those pixels and gives you text you can paste into an email, a Word document, a spreadsheet or a translation tool. This image to text converter uses Tesseract, a highly accurate open-source OCR engine originally developed by HP and later maintained with support from Google, running directly in your browser.

How to Extract Text From an Image

  1. Add your images. Drag and drop them, click to choose files, or paste a screenshot with Ctrl+V (Cmd+V on Mac). Scanned PDFs work too.
  2. Choose the language of the text. Selecting the right language makes a big difference to accuracy, especially for accented letters.
  3. Click Extract text. The first time you use a language, its recognition model (a few megabytes) is downloaded and then cached by your browser.
  4. Check and correct the text in the result box, then copy it or download it as a .txt file or a searchable PDF.

Supported Languages

You can recognise text in English, German, French, Spanish, Italian, Portuguese, Dutch, Polish, Turkish, Swedish, Danish, Norwegian, Finnish, Czech, Romanian, Hungarian, Greek, Russian, Ukrainian, Arabic, Hindi, Bengali, Urdu, Chinese (Simplified and Traditional), Japanese, Korean, Thai, Vietnamese and Indonesian. Select up to three languages at once for documents that mix languages, such as an English and Hindi form, or a German document with English terms.

Tips for the Most Accurate Results

TipWhy it helps
Use good, even lighting and avoid shadowsOCR works by contrast between text and background
Hold the camera straight above the pageTilted or curved lines are harder to read
Crop to the text you needLess background means fewer stray characters
Keep "Enhance image" on for photosGreyscale, upscaling and contrast boost help small or faint text
Choose the correct languageThe engine uses a dictionary and character set for each language
Use high-resolution scans (300 DPI)Tiny text in low-resolution images loses detail

Printed text in clear fonts is usually recognised with more than 95% accuracy. Handwriting, decorative fonts, very small text, low-contrast images and complex layouts (tables, multiple columns) are harder, so always proofread the result. The confidence score gives you a quick sense of how reliable the recognition was.

What Is a Searchable PDF?

A searchable PDF looks exactly like your original image or scan, but has an invisible layer of recognised text behind it. That means you can search it with Ctrl+F, select and copy text, and have it indexed by document management systems, while keeping the original appearance. Tick "Also create a searchable PDF" before extracting, and a Download searchable PDF button appears with all your pages combined into one file.

Common Uses

  • Copy text from screenshots of apps, videos, presentations or error messages.
  • Digitise paper documents: letters, receipts, invoices, recipes and notes.
  • Quote from books and articles without retyping.
  • Make scanned PDFs searchable for archives and research.
  • Translate text in photos: extract it here, then paste it into a translator.
  • Edit scanned forms: extract the text, or fill the form with our Fill PDF Form tool.

Private OCR in Your Browser

Many online OCR services upload your images to their servers, which isn't ideal for ID cards, contracts, bank statements or medical letters. Here, recognition happens in your browser using WebAssembly. The only things downloaded are the OCR engine and the language models, never your images. After the first use, the models are cached, so recognition starts faster and even works offline.

Frequently Asked Questions

Is this OCR tool free?

Yes. There's no sign-up, no watermark and no limit. Process up to 20 files at a time and as many batches as you like.

Can it read handwriting?

Neat, printed-style handwriting can sometimes be recognised, but accuracy is much lower than for typed text. Joined-up handwriting usually isn't readable.

Can I extract text from a PDF?

Yes. Scanned PDFs are processed page by page (up to 30 pages). If your PDF already contains selectable text, the PDF to Text tool is faster and exact.

Why is the first run slower?

The OCR engine and language model are downloaded the first time. After that they're cached by your browser.

Are my images uploaded?

No. Text recognition runs entirely on your device.