PDFCure
All tools

Extract Text from a Photo (OCR), Free

Pull the text out of a photo or screenshot — 14 languages, all in your browser.

Most tools run entirely on your device

Select an image

Click to choose, or drop a file here

You can also paste (Ctrl+V / Cmd+V)

Most tools run entirely on your device

About extracting text from an image (OCR)

A photo of a printed page, a screenshot of a document, or a picture of a sign or receipt often has text you'd rather have as actual selectable, copyable text. This tool reads the text out of an image using optical character recognition.

It runs Tesseract.js — the same OCR engine behind OCR PDF, pointed at a single image instead of a whole document — entirely in your browser via WebAssembly. The engine's language data downloads once on first use (a few megabytes) and is cached after that; the image itself is never uploaded. Pick the right language for the best accuracy, and expect better results from a clear, well-lit, high-resolution photo than a blurry or low-contrast one.

Supported files

Accepts JPG, PNG, WebP and other common images. Produces the extracted text, ready to copy.

Is my file uploaded?

No. OCR runs entirely in your browser with Tesseract.js — the image is never uploaded. Only the one-time, generic OCR language-data download talks to a third party, never your image.

Common problems

The extracted text is inaccurate or garbled
OCR accuracy depends heavily on image quality — make sure the text is in focus, well-lit, and not at a steep angle. Also confirm you picked the right language, since the wrong one measurably hurts accuracy.

How to Image to Text (OCR)

  1. 1

    Add an image

    Drop in a photo or screenshot with text in it.

  2. 2

    Pick the language

    Choose the language the text is written in — 14 supported.

  3. 3

    Extract

    Click Extract text; recognition runs in your browser. Copy or edit the result.

Image to Text (OCR) — frequently asked questions

Does it work on handwriting?+

Poorly — OCR is built for printed/typed text. Clear printed text at a decent resolution works best.

Is my image uploaded?+

No. Recognition uses an on-device WASM model. The first run downloads the language data (a few MB), then it's cached.

Which languages?+

14: English, Spanish, French, German, Italian, Portuguese, Dutch, Russian, Arabic, Hindi, Japanese, Korean, and Simplified/Traditional Chinese.

Is there a free way to extract text from a photo (OCR)?+

Yes — this tool runs OCR on the image entirely in your browser, free and with nothing uploaded.

Do you upload my files to a server?+

No — every tool here processes your files entirely on your device, and nothing is uploaded to a server. The only exception is the AI tools, which send the extracted text (not the file) to Claude to do their work.

Is there a file size limit?+

There's no artificial limit we impose, but since processing happens in your browser, very large files (500+ MB or 1,000+ pages) are limited by your device's memory rather than by us.