Identity & KYC

ID Document & Passport OCR API — Automate KYC in Seconds

Extract name, DOB, document number, nationality, expiry and MRZ from passports, national IDs and driving licences automatically. Power KYC and onboarding flows. Free to try.

6 min readUpdated April 14, 2026
<2 s
average extraction time per identity document

What DocPeel extracts

No fixed columns or rigid schema. The LLM reads your document and returns clean, structured JSON automatically — or you define your own template to control the exact output shape.

Smart auto-extraction
Upload any document and the LLM intelligently surfaces all relevant data as clean JSON. No schema setup, no field mapping — it adapts to whatever your document contains.
Custom templates
Need specific field names, data types, or a fixed output structure? Define a template once and every extraction follows your schema exactly.

Identity documents in digital workflows

Every regulated business — banks, insurance companies, property lettings agents, healthcare providers — requires identity verification. Customers upload a photo of their passport or driving licence, and someone on the back end has to manually key the details into the system.

This creates a bottleneck that slows onboarding, frustrates customers who expect instant decisions, and costs significant staff time at scale. A staffing agency onboarding 200 contractors a month spends around 50 hours just entering ID data.

DocPeel extracts all structured fields from an uploaded ID document in under two seconds, eliminating the manual step entirely.

Document types supported

DocPeel supports passports (all ICAO-compliant formats), national identity cards (European, Middle Eastern, Asian, and Latin American formats), driving licences (UK, US, EU, Australian), and residence permits.

Both the visual inspection zone (VIZ) — the human-readable printed fields — and the machine-readable zone (MRZ) at the bottom of the document are extracted and cross-referenced. Where the MRZ data and VIZ data differ, both are returned with a flag, allowing downstream verification logic to handle the discrepancy appropriately.

Security and compliance considerations

Identity documents are personally identifiable information (PII) subject to GDPR, CCPA, and similar regulations. DocPeel processes each document in an isolated sandbox and discards the source file immediately after extraction unless you explicitly enable document storage.

Extracted data is never used for model training. The API supports field-level masking — for example, you can receive name and expiry date without receiving the document number — to implement data minimisation at the extraction layer.

DocPeel is not an identity verification or fraud detection service. It extracts and structures the data on the document. Liveness checks, database cross-referencing, and fraud scoring are provided by specialist KYC vendors and should be layered on top of the extraction step.

Integrating ID extraction into onboarding flows

The most common pattern is a file upload in an onboarding form that calls the DocPeel API, receives the extracted fields, and pre-fills the remaining form fields for the user to confirm. This eliminates typing errors, speeds up completion, and improves data quality in the CRM or core system.

Alternatively, a back-office workflow can batch-process uploaded ID documents overnight and update customer records without a synchronous API call in the user flow.

Who uses this

  • Financial services teams automating KYC onboarding
  • Property lettings agencies verifying tenant identities
  • HR teams collecting employee identity documents
  • Healthcare providers verifying patient identities
  • Sharing economy platforms verifying host or driver IDs

Export formats

JSONCSVWebhookGoogle Sheets

Native integrations

WebhooksGoogle SheetsSlack

Frequently asked questions

Does DocPeel verify that the document is authentic?

No. DocPeel extracts the data from the document as presented. Document authentication, liveness detection, and fraud scoring require a specialist KYC provider and should be layered on top of the extraction step.

Can it extract data from photos taken on a phone?

Yes. Images taken on a smartphone — including photos with background clutter and mild lens distortion — are pre-processed before extraction. For best results, the document should be well-lit, flat, and fully in frame.

Does it read the MRZ on passports?

Yes. Both MRZ lines are decoded and returned as structured fields alongside the visual zone data. Check digits are validated and a flag is raised if any check digit does not match.

How is identity data handled under GDPR?

Source documents are discarded immediately after extraction by default. Extracted data is never used for model training. DocPeel supports right-to-erasure requests via the API, allowing you to purge individual extraction records on demand.

Ready to automate your identity & kyc workflow?

Start free and extract your first document in minutes. No credit card, no template configuration, no per-document fees to start.