Copyable requests
curl
curl -F "file=@scan.png" https://agentmediatools.com/api/ocrOCR Extraction API
Extract text from an image or PDF
Extract text from uploaded images and PDFs with Tesseract, pdftotext, or pdf-parse. Returns text, engine, word count, and character count through REST and MCP.
✓ Transparent usage terms✓ REST + MCP✓ Real browser tool
Working examples
Copy it into your stack.
Upload a scan or PDF, or provide a public URL. The local extraction pipeline returns plain text and document counts as JSON.
Example JSON response
{"success":true,"text":"Invoice 1042","engine":"tesseract","word_count":2,"char_count":12}Download URLs are temporary. Save results to your own storage when the workflow needs durable retention.
What you can build
- ✓ Extract text from scans before LLM processing
- ✓ Make invoice and receipt text searchable
- ✓ Convert PDF text into downstream structured workflows
Frequently asked questions
Which engines are used?
PDFs use pdftotext or pdf-parse; images use the server Tesseract installation.
What does the response contain?
The JSON response includes extracted text, engine, word count, and character count.
Does image OCR always work?
Image OCR requires Tesseract on the server; PDF text extraction has separate local fallbacks.
One tool now, one integration later
Test it in the browser. Automate it when ready.
The same Agent Media Tools account connects this operation to the wider Tool API and MCP catalog.