Image to Text (OCR)
Extract text from any image, photo or scan — right in your browser.
The OCR engine (~2–15MB depending on language) downloads once on first use and runs entirely on your device's CPU. This may take longer on older phones or slow connections — subsequent uses in the same session are much faster.
Drop an image here
or click to browse (JPG, PNG, WebP · up to 20MB)
You can also paste an image with Ctrl/Cmd+V
Frequently Asked Questions
Is my image uploaded to a server?expand_more
No. Text recognition runs entirely in your browser using Tesseract.js, an open-source OCR engine compiled to WebAssembly. Only the OCR engine files themselves are downloaded from a public CDN on first use — your image never leaves your device.
Why is OCR slow the first time?expand_more
The engine and language data need to download once (a few MB) and initialize before the first recognition. This is a one-time cost per session — trying another image right after will be noticeably faster.
How can I get the most accurate results?expand_more
Use a clear, well-lit, high-resolution image with the text upright and not too small. Avoid heavy blur, glare, or extreme angles — straightening a skewed photo beforehand also helps accuracy.