ScanLocal

How to use

Extract text from images entirely in your browser — nothing is uploaded.

• 📜 Default: Tesseract — most reliable browser engine
• 🚀 Fast: PaddleOCR — printed text, experimental browser path
• ✍️ Handwriting: TrOCR — accurate on handwriting (500 MB)
• 🧠 Smart: printed-text transformer OCR
• 🔭 Qwen: experimental Qwen2-VL document reader, very large download

Drop an image, wait for processing, then copy the extracted text.