Turn tax, passbook, and civil-registration documents into structured data in one call.
Feed in a photo or scan of any supported document type and get back clean, structured fields — document type, amounts, dates, and account numbers — normalized to a single schema. One endpoint covers tax forms, bank passbooks, and civil-registration paperwork, so your workflow doesn't need a different parser for each.
Multi-document classification
Automatically detects whether the input is a tax document, passbook, or civil-registration form before extraction, so callers don't need to pre-sort files by type.
Normalized financial fields
Amounts, dates, and account numbers are parsed and formatted consistently across document types — no per-document regex or cleanup on your end.
Built for scanned and photographed batches
Tuned on real-world submissions — folded passbooks, faded stamps, skewed scans — not just clean digital originals.
The engine first identifies which document type it's looking at, then routes to the right extraction and validation logic for that form — so a tax filing and a bank passbook don't get forced through the same generic template.
Get API access in days, or bring us in to run the full workflow for you — sovereignty by design at every step.