Document AI

Tatvora OCR AI

Turn documents into usable data.

Tatvora OCR AI converts unstructured documents into data your application can act on. Send an image, a scanned page, a multi-page PDF or a DOCX file and receive clean, machine-readable text and structured fields in a predictable JSON response. It removes the manual data-entry step that sits between a document arriving and a business process being able to continue.

POST https://api.tatvora.com/api/v1/ocr
POST https://api.tatvora.com/api/v1/ocr
curl -X POST https://api.tatvora.comPOST /api/v1/ocr \
  -H "Authorization: Bearer $TATVORA_API_KEY" \
  -F "document=@invoice.pdf"
How it works

The OCR pipeline

  1. Document or image
  2. Tatvora OCR AI
  3. Text + structured fields
  4. Your application
See it work

What you send, and what you get back

A worked example of a single OCR AI call, end to end.

POST /api/v1/ocr

1 · You send

INVOICE
INV-1024
10 Aug 2026
Total ₹ 12,850

JPG · PNG · PDF · DOCX · scanned pages

2 · We process

Tatvora OCR AI text + layout extraction

3 · You receive

Invoice number INV-1024
Invoice date 2026-08-10
Customer Example Company
GST number 24AAAAA0000A1Z5
Total 12,850
{
  "success": true,
  "invoice_number": "INV-1024",
  "date": "2026-08-10",
  "customer": "Example Company",
  "total": 12850
}

Sample data for illustration. Fields returned depend on the document you submit. The document is processed in memory and discarded when the response is sent — nothing is stored.

Capabilities

What OCR AI can do

  • Text extraction from images and scans
  • OCR processing for low-quality and photographed pages
  • Document parsing into structured fields
  • Multi-page PDF processing
  • DOCX and office document handling
  • Structured text extraction from forms and tables
  • Batch document processing
  • Document digitisation pipelines
  • REST API integration with JSON responses
Use cases

Where it is applied

  • Invoice processing and accounts payable automation
  • HR and employee document digitisation
  • Banking document processing
  • Insurance claim and policy documents
  • KYC document extraction
  • Government and public records digitisation
  • Application and enrolment forms
  • Receipt capture and expense workflows
  • Replacing manual data entry in back-office systems
API reference

Request and response

Authenticate with a bearer API key over HTTPS. Upload a file as multipart/form-data and receive a JSON response.

Request fields

  • document — file part, multipart/form-data
  • Authorization: Bearer YOUR_API_KEY — required header

Endpoints and payloads shown on this site are illustrative examples of the published interface. Never expose a secret API key in client-side code.

200 OK — example response
{
  "success": true,
  "request_id": "req_8f2c41d0",
  "pages": 3,
  "text": "Extracted document content...",
  "fields": {
    "invoice_number": "INV-2043",
    "invoice_date": "2026-03-14",
    "total": "1,248.00"
  },
  "processing_time_ms": 412
}
FAQ

OCR AI questions

Yes, including multi-page PDFs. Extracted text is returned with page attribution so you can map content back to its source page.

Yes. Scanned pages, photographed documents and images are all supported, alongside digital PDFs and DOCX files. Capture quality still affects results, so we recommend running representative samples through an evaluation key before you commit to a plan.
More AI APIs

Combine OCR AI with the rest of the platform

View all AI products

Try Tatvora OCR AI

Request an evaluation key and validate the model against your own data before choosing a plan.

Questions? Email support@tatvora.com