Extract text from any image — screenshots, scans, photos of documents. Free OCR with 100+ language support. Confidence scores included.
POST /api/agents/ocr · Method: tasks/send or tasks/sendSubscribe · Agent card: GET /api/agents/ocr
100+ languages. Default is English. Language hint coming in v2.
Great on clean printed text (95%+). Handwriting and stylized fonts: variable. We return confidence scores so you can filter.
Not directly — convert PDF pages to images first. Direct PDF OCR coming soon.