Documents — Vend
Thai Document Intake
Turn any incoming Thai document into structured, usable data in one call.
Get API AccessPrivate beta only
// BUILT FROM
Thai OCR Core
Document Parsers
Thai Document Intake
Turn any incoming Thai document into structured, usable data in one call.
Thai Document Intake takes tax forms, bank passbooks, and civil-registration paperwork off the desks of back-office teams and turns them into clean, structured fields the moment they arrive. One shared OCR engine reads every document type, so a folded passbook and a stamped tax filing come out the other side in the same predictable shape — no manual keying, no per-document scripts to maintain.
Broad document-type coverage
Tax, passbook, and civil-registration documents all route through the same intake pipeline, so growing coverage doesn't mean bolting on a new tool.
Structured output, ready to use
Every document lands as normalized, typed fields your downstream systems can consume directly, not raw text you still have to parse.
Built for real-world scans
Tuned on phone-camera photos, faded stamps, and skewed scans — the documents that actually show up, not studio-quality samples.
Every capability below already ships as its own API — this solution just orchestrates them into one workflow.
Every document is classified first, then routed through the OCR and parsing logic built for that type — so a tax filing and a passbook each get the extraction they actually need.
Capture
A photo or scan of the incoming document is uploaded.
OCR Extraction
The shared OCR engine reads every field on the page.
Field Parsing
Fields are classified, normalized, and validated for the detected document type.
Structured Output
Clean, typed fields are returned, ready to drop into your workflow.
Get API access in days, or bring us in to run the full workflow for you — sovereignty by design at every step.