Screenshot OCR without sending the file
Screenshot OCR without sending the file?
Use Local OCR when you need the words from a screenshot or a scan, plus a searchable PDF, without an upload queue. Discord, WhatsApp, iMessage, and Slack screenshots are images. Auto uses English and does not detect the script. Screenshots from Discord, WhatsApp, iMessage, and Slack, plus phone photos of signs and slides.
WhatsApp Help: media and documents; WhatsApp Help: longer videos
Last updated
Use Local OCR when you need the words from a screenshot or a scan, plus a searchable PDF, without an upload queue. Discord, WhatsApp, iMessage, and Slack screenshots are images. Auto uses English and does not detect the script.
Reviewed 12 October 2026
What it is for
- Screenshots from Discord, WhatsApp, iMessage, and Slack, plus phone photos of signs and slides.
- Receipts and invoices — with the caveat that totals are the first thing to re-check.
- Scanned PDFs that have no real text layer, exported as searchable PDF.
- Native-text PDFs, where embedded text can be reused until you Force OCR.
Languages
Shipped recognition packs: English, Simplified Chinese, Traditional Chinese, Japanese, Korean, Spanish, French, German, Portuguese, Hindi, Arabic. You choose a language before running. Auto does not detect script; it falls back to English. If you leave Auto on a Chinese scan, expect English-biased garbage rather than magic. The page locale only preselects a pack; every shipped language stays in the selector.
Privacy and limits
Recognition runs in the tab after you start it. Runtime assets load from this origin, not from a third-party OCR API. Encrypted PDFs are rejected; we do not bypass passwords.
Accuracy drops on heavy JPEG compression, skewed pages, tiny UI type, handwriting, and mixed receipts. We do not advertise a single accuracy percentage.
Searchable PDF overlay uses Tesseract word boxes. CJK export needs the bundled font. Force OCR on a digital PDF may stack an OCR layer on top of the original text layer — that limitation is disclosed in the tool.
Related
Screenshot OCR · Searchable PDF from a scan · OCR benchmark dataset · Remove PDF metadata online · Image to text without uploading · Receipt OCR · 2026 multilingual OCR benchmark · Methodology.