OCR.space
ocrspaceOCR.space provides a free and paid OCR API for extracting text from images and PDFs, returning results in JSON format.
Acciones disponibles (1)
Cada acción es una operación que el agente puede ejecutar contra este conector. Haz clic en una acción para ver sus parámetros.
OCR Parse ImageOCRSPACE_OCR_PARSE_IMAGE_POSTAcciónTool to submit image or pdf to ocr.space for ocr processing.
OCRSPACE_OCR_PARSE_IMAGE_POSTAcciónTool to submit image or pdf to ocr.space for ocr processing.
Parámetros de entrada
urlstringPublic URL of image or PDF
filestringbinaryBinary content of image or PDF file (multipart upload)
scalebooleanWhether to scale low-resolution image
isTablebooleanWhether to attempt table recognition
filetypestringFile type hint for URL or base64 input
languagestringenumOCR language code
engspadeuOCREngineintegerenumOCR engine: 1=standard, 2=experimental
12base64ImagestringBase64-encoded image data (data URI)
detectOrientationbooleanWhether to detect text orientation
isOverlayRequiredbooleanWhether to return text overlay data
isCreateSearchablePdfbooleanWhether to return searchable PDF
isSearchablePdfHideTextLayerbooleanWhether to hide text layer in searchable PDF
Parámetros de salida
dataobjectObligatorioData from the action execution
errorstringError if any occurred during the execution of the action
successfulbooleanObligatorioWhether or not the action execution was successful or not