Provide a document URL and its language, then ask AI to extract the text needed for your task.
Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.
Recognize document text and summarize invoice details from the extracted pages.
/oo OCR.space: Extract text from [public PDF URL] using English recognition and table-aware parsing. List invoice numbers, totals, and due dates, and flag any pages with processing errors.
Set up oo CLI and the oo Skill in your agent.
Install OOMOL →Connect an OCR.space API key from the API signup page.
Connect OCR.space →Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →Choose Your Agent
The integration processes a public image or PDF URL, or Base64 file content, and supplies combined text, page results, and processing errors. It also reads monthly conversion statistics.
Extract page text with language and orientation options, or inspect monthly conversion counts.
Extract text from a public image or uploaded Base64 file by calling OCR.space and returning normalized page results.
Leina 
Wanta 
ocrspace.extract_text Fetch OCR.space conversion statistics for the current month or the previous month.
ocrspace.get_conversion_stats No matching tools.
It provides combined text and per-page results, together with processing status and errors. Word position information can be requested.
Yes. Request orientation detection, image scaling, or table-aware parsing and specify the document language.
Conversion statistics cover the current month or the previous month, with totals by OCR engine.
Manage which optional storage OOMOL can use. You can change these choices from the footer at any time.