Uttir

Image to Text (OCR)

Extract text from any image using OCR. Runs entirely in your browser — your image never leaves your device. Supports English, Spanish, French, German, and more.

Image to Text (OCR) — Pull text out of any image — a screenshot, a scanned document, a photo of a sign, a PDF rendered as an image. The OCR engine runs in your browser using Tesseract.js (the JavaScript port of the Tesseract OCR, originally developed at HP and now maintained by Google).

OCR runs entirely in your browser using Tesseract.js. The image is processed locally; nothing is sent to any server.

Was Image to Text (OCR) useful?

What is image to text (ocr)?

Pull text out of any image — a screenshot, a scanned document, a photo of a sign, a PDF rendered as an image. The OCR engine runs in your browser using Tesseract.js (the JavaScript port of the Tesseract OCR, originally developed at HP and now maintained by Google).

Unlike most online OCR tools, your image is processed locally. It never leaves your device. This is the right tool for sensitive documents (medical records, financial statements, IDs) and for anyone who values their privacy.

How to use it

  1. Drop or upload an image

    JPG, PNG, WebP, BMP. The image is processed locally.

  2. Pick a language

    English is the default. Pick another for non-English text.

  3. Wait for the OCR to finish

    First run takes a few seconds while the engine loads. Subsequent runs are faster.

  4. Copy or download the extracted text

    Click "Copy" to put it on your clipboard, or "Download" to save a .txt file.

Frequently asked questions

Related tools