Document Intelligence · OCR
Turn any printed or handwritten document into clean, machine-readable text with a single, general-purpose OCR call.
Overview
What the Document to Text OCR API does
FinHub's Document to Text OCR API converts printed and handwritten documents — forms, letters, notes and scanned records — into structured, searchable text, preserving layout where it matters. It's built as a general-purpose extraction layer underneath FinHub's specialized document APIs, with consent capture and a tamper-evident audit log on every call.
Inputs
- Document (PDF or image, printed or handwritten)
- Language hint
- Consent artifact ID
Returns
- Full extracted text
- Per-line/word confidence scores
- Detected language
- Layout metadata
POST /v1/ocr/document-to-text
How it works
Three steps to a verified result
Upload the document
Send a printed or handwritten document image or PDF with a consent artifact over a single authenticated call.
We run OCR extraction
FinHub's OCR engine recognizes printed and handwritten text, scoring confidence at the line and word level.
Get machine-readable text
Receive full extracted text with confidence scores and optional layout metadata — sealed to your audit trail.
Use cases
Where teams use Document to Text OCR
- Form and application digitization
- Correspondence and letter archival
- Handwritten note capture for claims processing
- Building custom document pipelines on raw OCR text
FAQ
Document to Text OCR API — FAQs
Common questions about FinHub's Document to Text OCR API.
Yes. The API is tuned for both printed and handwritten text and returns confidence scores so you can route low-confidence extractions to manual review.
More verification APIs
Explore related APIs
Ready to add Document to Text OCR to your flow?
Book a demo and see the API return a verified result on your own test data in minutes.