ToolDashy

Image to Text (OCR)

Turn a screenshot, photo of a document or scanned page into editable text. Text recognition (OCR) runs entirely on your device, so your images are never uploaded.

Your files are processed locally in your browser and are not uploaded to our servers.

How to use image to text (ocr)

  1. 1Drag in a JPG, PNG or WebP image, click to choose one, or paste a screenshot with Ctrl/⌘ + V.
  2. 2Wait a few seconds while the text is recognised — a progress bar shows each step.
  3. 3Check the extracted text against the image and correct anything that was misread.
  4. 4Copy the text or download it as a .txt file. If the text is sideways, rotate the image and it runs again.

About this tool

This tool uses Tesseract, a widely used open-source OCR engine, compiled to WebAssembly so it runs inside your browser. The engine and its English language model are served from this site and cached after the first use (a one-time download of roughly 4–7 MB), and the image is processed on your own device — it isn't sent to any server.

It works best on clear, printed English text: screenshots, documents, receipts, book pages and signs photographed straight on. Example: a screenshot of an error message or an article usually comes out almost word for word, while a blurry photo taken at an angle needs more correction.

Limitations: only English is supported; handwriting, decorative fonts, very small text and low-contrast or busy backgrounds are often misread; and the layout of tables and columns isn't preserved. Large photos are scaled to at most 3,000 pixels on the longest side to keep memory use manageable on phones. Always proofread the result before relying on it.

Frequently asked questions

No. The OCR engine runs inside your browser and the image never leaves your device. The only downloads are the engine and English language files, which come from this site and are cached for next time.

Related tools