Read Chinese out of an image — Simplified and Traditional, and the same pack reads Japanese and English, so a page mixing all three needs no second run. It is the one pack trained on vertical lines, handwriting and pinyin, which is why it is also the default: a CJK screenshot on a fresh visit gets an answer rather than mojibake. At 16 MB it is the largest of the twelve.
How it works
- Drop an image or PDF. Text detection runs immediately.
- Pick your language pack (downloaded once, 8–17 MB) and press Read text.
- Copy the lines, or download .txt / .json. PDFs are read cover to cover.
Questions
- Does it handle vertical text and handwriting?
- Yes — this pack is trained on both, along with pinyin annotations. Vertical lines come back as separate lines in reading order. Handwriting is harder than print for any OCR model, so check the per-line confidence scores.
- Does my file get uploaded?
- No. The models and all processing run inside your browser on your own device. You can verify this yourself: open your browser’s DevTools, watch the Network tab, and process a file: there are no uploads. After the first visit most tools also work fully offline.
- Which languages are supported?
- 106 languages across Latin, Cyrillic, Arabic, Devanagari, CJK, Greek, Thai, Tamil and Telugu scripts. Bengali is the one major gap, since no v5 model exists for it yet, and the picker says so rather than guessing.
- How accurate is it?
- On clean document text, the measured character error rate is under 2%, and every line carries a confidence score so you can see which ones to check. Handwriting and low-resolution photos will read worse.
- Does it read scanned PDFs?
- Yes. Digital PDFs are read from their own text layer, with exact characters at exact positions. Scanned pages go through detection and recognition, and mixed documents use both.