OCR text extraction
Pull the text out of a photo, scan, or screenshot. The recognition model downloads once on first use, then everything runs locally in your browser — nothing is uploaded.
Drop an image here, or click to choose one
Works with photos, scans and screenshots. First use downloads a small language model.
When you'd use this
- Pulling text out of a scanned document or photo of a page
- Getting editable text from a screenshot instead of retyping it
- Extracting a quote or paragraph from an image of printed text
Works best on clear, well-lit, reasonably horizontal text. Handwriting and heavily stylised fonts are less reliable.