What documents can the KYC OCR API process?

PicToText supports passports, national ID cards, and driver licenses. Each document type has dedicated extraction logic and returns structured fields for identity verification workflows.

Is this a full KYC compliance platform?

No. PicToText provides the OCR and structured data extraction layer. You can connect the output to your own KYC rules, review queues, fraud checks, storage systems, or verification providers.

Can I use the API for global identity documents?

Yes. The API supports global passport formats, many national ID card layouts, and driver licenses across supported regions. Field availability depends on the document type and country.

Can PicToText process mobile document photos?

Yes. The models are designed for real-world captures, including mobile photos with rotation, blur, glare, and varied backgrounds. Clear, full-document images still produce the best results.

Does the API return raw text or structured JSON?

The API returns structured JSON fields such as names, document numbers, dates, address fields, MRZ data, and document type information when available.

How is sensitive identity data handled?

API requests use encrypted transport, stored content is encrypted, and uploaded files plus OCR results are automatically purged after 30 days.

KYC OCR API

Ship identity document intake without building OCR plumbing

Name: PicToText OCR API
Author: PicToText

Send passport, national ID, or driver license images to one OCR layer. PicToText returns document-specific structured data your onboarding backend can route, store, and review.

Get API Key View API Docs

Built for developer-owned KYC pipelines, not a black-box compliance suite.

Document intake pipeline

One request moves raw document images into typed structuredData.

Passport

passport

ID card

cn_id_card

Driver license

us_drivers_license

curl -X POST "https://pictotext.io/api/v1/ocr" \
  -H "Authorization: Bearer sk_live_..." \
  -F "[email protected]" \
  -F "documentType=passport"

POST/api/v1/ocr

FORMimage + documentType

MODELdetect + extract

OUTPUTstructuredData

Review queue

Risk rules

User profile

Real response structures by document type

KYC flows span multiple identity documents. These examples use the documented response shape for passport, Chinese ID card, and US driver license endpoints.

Passport

passport

docs

passportNumbernamebirthDayexpiryDaymrz

{
  "passportNumber": "P12345678",
  "name": "JOHN MICHAEL DOE",
  "gender": "Male",
  "birthDay": "1990-01-01",
  "birthPlace": "NEW YORK, USA",
  "issueDay": "2020-01-01",
  "expiryDay": "2030-01-01",
  "issuePlace": "WASHINGTON D.C.",
  "nationality": "UNITED STATES OF AMERICA",
  "mrz": "P<USADOE<<JOHN<MICHAEL<<<<<<<<<<<<<<<<<<<<<\n1234567890USA9001011M3001012<<<<<<<<<<<<<<08"
}

ID card

cn_id_card

docs

namegenderdateOfBirthidNumbervalidityPeriod

{
  "name": "张三",
  "gender": "男",
  "ethnicity": "汉",
  "dateOfBirth": "1990-01-01",
  "address": "北京市朝阳区xxx街道xxx号",
  "idNumber": "110101199001011234",
  "issuingAuthority": "北京市公安局朝阳分局",
  "validityPeriod": "2010.01.01-2030.01.01"
}

Driver's license

us_drivers_license

docs

firstNamelastNamelicenseNumberdateOfBirthexpiryDate

{
  "firstName": "JOHN",
  "lastName": "DOE",
  "licenseNumber": "D123456789012",
  "dateOfBirth": "1990-01-01",
  "issueDate": "2020-01-01",
  "expiryDate": "2025-01-01",
  "address": "123 MAIN STREET",
  "city": "LOS ANGELES",
  "state": "CA",
  "zipCode": "90001",
  "gender": "M",
  "height": "6'00\"",
  "eyeColor": "BRO",
  "vehicleClass": "C",
  "restrictions": "NONE"
}

Integrate it like infrastructure

Keep your own decisioning, review UX, and storage rules. PicToText handles document OCR and field extraction before your KYC backend takes over.

Upload from any intake surface

Accept document images from web, mobile, support tools, or backend jobs.

Pass the document type

Use the matching documentType so the API applies the right schema and field extraction model.

Consume typed JSON

Receive document-specific structuredData instead of screenshots or loose OCR text blocks.

Route downstream

Send the result into profile creation, risk checks, manual review, or your own KYC rules.

Coverage for the documents KYC teams actually collect

Use the same integration pattern across passports, national ID cards, and driver licenses while preserving document-specific fields.

Passport OCR API

Extract MRZ, passport number, name, nationality, birth date, issue date, expiry date, issue place, and other documented passport fields.

View API Docs

ID Card OCR API

Handle national identity cards across countries, layouts, and native scripts.

View API Docs

Driver's License OCR API

Extract license numbers, dates, address fields, and PDF417 data for supported licenses.

View API Docs

Designed for developer-owned KYC systems

PicToText fits into your existing onboarding stack. Use it before manual review, risk scoring, document storage, or downstream verification providers.

REST API for backend ingestion
Document-specific structuredData responses
Works with your own fraud, risk, and compliance logic
Scales from testing to higher-volume KYC workflows

Read quickstart

Security and data handling built into the workflow

Identity documents contain sensitive data. PicToText uses encrypted transport, encrypted storage, and automatic cleanup windows so teams can reduce unnecessary data retention.

TLS-protected API requests
Encrypted storage for uploaded content and OCR results
Uploaded files and OCR results are automatically purged after 30 days
API keys and dashboard controls for operational access

Where KYC OCR fits

Fintech onboarding

Crypto exchange verification

Lending applications

Marketplace seller checks

Mobility and gig platform onboarding

Remote account opening

KYC OCR API FAQ

Start building automated KYC document intake

Use PicToText to turn identity document images into structured data your onboarding workflow can use.

Get API Key Contact Sales