Drop a Hindi image and the text comes out as Unicode Devanagari, the kind you can paste into Word, Google Docs, WhatsApp or a government form. Matras, half letters and conjuncts (क्ष, त्र, ज्ञ, श्र) are kept as typed text, not pictures.
On our Hindi test images the default engine (Tesseract 5) got 99.7% of characters right. It also reads Marathi, Nepali and Sanskrit, which share the script.
Nothing is uploaded. The image is read by a model that runs inside your browser, so it works for private documents and keeps working on a slow connection once the model is cached.
Old Kruti Dev and other legacy fonts
If a document was typed in Kruti Dev or another legacy font, copying the text gives gibberish. Taking a screenshot of it and reading it here gives proper Unicode Hindi instead, which works everywhere.
How to do it
- Make sure Hindi · हिन्दी is selected.
- Drop, paste or photograph the page.
- Check the text (amber lines first), then copy or download Word.
हिंदी OCR: फ़ोटो से हिंदी टेक्स्ट
हिंदी में लिखी किसी भी फ़ोटो, स्कैन या स्क्रीनशॉट से यूनिकोड टेक्स्ट निकालें, जिसे आप Word, Google Docs या WhatsApp में सीधे इस्तेमाल कर सकें। मात्राएँ और संयुक्त अक्षर (क्ष, त्र, ज्ञ) टेक्स्ट के रूप में आते हैं।
आपकी फ़ोटो कहीं अपलोड नहीं होती। पढ़ने वाला मॉडल एक बार डाउनलोड होकर आपके ब्राउज़र में ही चलता है। हमारी जाँच में 99.7% अक्षर सही पढ़े गए।
- ऊपर भाषा में "Hindi · हिन्दी" चुनें।
- फ़ोटो डालें, स्क्रीनशॉट पेस्ट करें (Ctrl+V) या कैमरा दबाएँ।
- पीले निशान वाली पंक्तियाँ जाँचें, फिर कॉपी करें या Word में डाउनलोड करें।
How accurate it is (measured, not claimed)
We render known text in each script as images in five styles: a clean screenshot, small 15 px text, a photo (rotated, soft focus, uneven light, JPEG), a dark-mode screenshot and a rough photo (low contrast, blurrier, more tilt, heavy JPEG). Each engine reads them in a browser, and we count the characters it gets right (100% minus the character error rate). The default engine for each script is the one with fewer character errors (within half a point, the one with more whole words right).
| Script | Engine | All | clean | small | photo | dark | rough | s / image |
|---|---|---|---|---|---|---|---|---|
| Hindi | Tesseract 5default | 99.7% | 100.0% | 100.0% | 100.0% | 100.0% | 98.2% | 0.5 |
| Hindi | PaddleOCR PP-OCRv5 | 96.7% | 99.4% | 96.7% | 98.5% | 94.0% | 94.7% | 1.8 |
Measured 2026-11-03 on Intel(R) Core(TM) i7-14700KF (28 threads), headless Chromium, no WebGPU adapter, cross-origin isolated. Real photos have not been validated for this tool. Generated images are easier than real photos of real paper, so treat these as a ceiling for printed text, not a promise. Tesseract was partly trained on font-rendered text, which may flatter it on generated images. The test text and the script that draws the images are in the project repository.
Private by design
The image is read by an open-source model that runs in your browser (PaddleOCR or Tesseract, both Apache-2.0). It downloads once, about 12 MB for most scripts, and is cached for next time. Your images, the text and your downloads stay on your device: there is no upload, no account and no log of what you read.
Questions people ask
Are my images uploaded to a server?
No. The reading model is downloaded to your browser once and runs on your own phone or computer. The image, the text and the files you download never leave your device. You can switch off your internet after the model has loaded and it still works.
Is it free? Is there a limit?
It is free, with no sign-up, no watermark and no daily cap. Because your own device does the work, there is no server cost for us to recover. Add as many images as you like; they are read one after another.
Which file types can I use?
PNG, JPG, WebP, GIF and BMP images, screenshots pasted with Ctrl+V, and photos from your camera. For a PDF, take a screenshot of the page or export it as an image first.
Is the output Unicode?
Yes. You get standard Unicode Devanagari that works in Word, Google Docs, email and WhatsApp, not a legacy font encoding.
Can it read a page with both Hindi and English?
Mostly. The Hindi model also knows Latin letters and digits, so English words in a Hindi page usually come through. For a page that is mainly English, choose English instead.
Does it work for Marathi?
Yes. Marathi uses the same Devanagari script, and the Hindi model reads it. A few Marathi-only letters, like ळ, are less common in training data, so check them.