Document APIs
Thai OCR Core
The engine behind every document API — read any Thai or English document in one call.
Get API AccessPrivate beta only
The engine behind every document API — read any Thai or English document in one call.
Thai OCR Core turns any scanned or photographed document into structured text with layout, confidence, and language detection attached. It's the shared recognition engine every AttenTech document API builds on, exposed directly for teams who need raw OCR on documents that don't fit a pre-built template.
Mixed Thai/English recognition
A single pass reads Thai script, English text, and mixed-language lines without needing a language hint up front.
Layout-aware output
Text comes back with its position and structure preserved — lines, blocks, and reading order — not just a flat text dump.
Per-line confidence scoring
Every extracted line carries a confidence score, so low-certainty text can be routed for review instead of trusted blindly.
The same recognition engine every AttenTech document API runs on: it reads Thai and English in a single pass, reconstructs the original layout, and scores every line for confidence — so low-certainty text can be routed for review instead of trusted blindly.
Get API access in days, or bring us in to run the full workflow for you — sovereignty by design at every step.