◌

OCR.space

OCR.space integration (AI, Productivity). Imported from open-connector.

API key2 native toolsIcon fallback

This catalogue entry describes the current repository definition. Availability, scopes, and production readiness should be confirmed during private-beta onboarding.

Native tools

POST

ocrspace_extract_text

Extract text from a public image/PDF URL or uploaded transit file by calling OCR.space.

/parse/image

8 parameters

Param	Type	Required	Description
url	string	optional	The public image or PDF URL to parse with OCR.space.
file	object	optional	A local transit image or PDF file to upload to OCR.space.
language	string	optional	The OCR language code to send upstream.
detectOrientation	boolean	optional	Whether OCR.space should auto-detect page orientation.
scale	boolean	optional	Whether OCR.space should scale the input image.
isOverlayRequired	boolean	optional	Whether OCR.space should return word-level overlay metadata.
isTable	boolean	optional	Whether OCR.space should apply table-aware parsing when possible.
ocrEngine	string	optional	The OCR engine version to request from OCR.space.

POST

ocrspace_get_conversion_stats

Fetch OCR.space conversion statistics for the current month or the previous month.

/conversions

1 parameter

Param	Type	Required	Description
startDate	string	optional	Set to lastMonth to fetch the previous month's conversion statistics.

Request private-beta access