Run OCR over hundreds of images in one pass: receipts, scans, screenshots, archives. Each image produces its own .txt, and the ZIP also carries one combined JSON with every line, its position and its confidence, ready for a script to consume.
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
- How many files can one batch take?
- Up to 500 files or 2 GB of input per run, dropped as loose files or a single ZIP. Items process one at a time on your device, nothing is uploaded, and the progress strip shows a per-item ETA. Bigger jobs: split into two drops.
- What do I get back?
- One ZIP: every processed file, named exactly like the single-file download would be, plus _report.txt and _report.json listing each input and what happened to it, including any that failed and why. A cancelled batch still downloads the items finished so far, with the report saying so.
- 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.