Image OCR
Extract readable text and confidence scores from screenshots, scans, receipts, and labels.
OCR Output
Extracted text and coordinates
Each line includes confidence and the source polygon so you can highlight regions in downstream workflows.
No OCR result yet
Submit an image to inspect extracted text line by line.
Use the API directly
Every run maps to POST /api/image/ocr/v1.
Pair OCR output with your existing image or document pipelines.
Useful when
- Extract text from receipts, invoices, and forms.
- Capture text from screenshots for searchable archives.
- Automate data entry from scanned documents.