Extracting structured data from invoices and contracts with one API call

Mediavox released a document analysis API that extracts structured data from invoices, contracts, and receipts in a single call, supporting Spanish and Portuguese. The multimodal AI endpoint handles scanned PDFs, Word files, and phone photos, returning entities like vendor name, tax ID, and totals with confidence scores. A session feature allows follow-up questions without re-uploading, and an integrity check automatically verifies arithmetic consistency.

I've been working on a document analysis API and wanted to share a pattern that saved me from writing custom parsers for every document type my clients throw at me. If you work with LATAM businesses, you know the pain: invoices in PDF sometimes scanned , contracts in Word, receipts as phone photos. Every client has a different format. Building regex parsers for each one is a nightmare that breaks every time the layout changes slightly. Instead of building N parsers, I use a single multimodal AI endpoint that: python import requests Upload and analyze in one call with open "invoice.pdf", "rb" as f: response = requests.post "https://mediavox.co/mvai/api/v1/documents/analyze", files={"file": f}, data={ "api key": "your key here", "question": "Extract: vendor name, tax ID, invoice number, date, line items with quantities and prices, subtotal, tax, total." }, timeout=60 result = response.json print result "answer" Human-readable summary print result "entities" Structured: {type: "vendor", value: "..."} print result "document type" "factura", "contrato", "recibo"... print result "session id" For follow-up questions The session persists the document context, so you can ask clarifying questions without re-uploading: follow up = requests.post "https://mediavox.co/mvai/api/v1/chat", json={ "api key": "your key here", "question": "What are the payment terms?", "session id": result "session id" } print follow up.json "answer" "Payment terms: 30 days net. Due date: August 15, 2026." The AI answers from the document only — no hallucinations from external knowledge. Input: a crumpled photo of a Colombian restaurant receipt low light, tilted { "document type": "recibo", "entities": {"type": "vendor", "value": "Restaurante El Portal", "confidence": 0.94}, {"type": "tax id", "value": "901234567-8", "confidence": 0.91}, {"type": "total", "value": "98700", "confidence": 0.97}, {"type": "tax", "value": "15800", "confidence": 0.89}, {"type": "date", "value": "2026-06-28", "confidence": 0.95} , "integrity": { "subtotal matches items": true, "tax calculation correct": true } } The integrity check catches arithmetic mismatches automatically — useful for expense auditing. If you use n8n, there's a community node n8n-nodes-mediavox that wraps all of this. Or use HTTP Request nodes directly — the API is straightforward REST. I published a ready-to-use workflow template: Extract invoice details and ask follow-ups https://mediavox.co/mvdevportal/static/n8n/documentpower-analyze-invoice.json — import it and replace the file path. Free tier: 100 requests/month. Enough to test with real documents. n8n-nodes-mediavox on npm Built this for LATAM businesses dealing with messy paperwork. If you're processing documents in Spanish/Portuguese and tired of custom parsers, this might save you time.