Bolt.new Tutorial5 min setupNo-code friendly

Add Driver's License OCR to Your Bolt.new App in 5 Minutes

Bolt.new scaffolds your full-stack UI. StructOCR reads the plastic cards. Here's the exact prompt and API call to wire them together for instant driver onboarding.

Diagram showing a driver's license photo uploaded in a Bolt.new app, sent to the StructOCR API, and returned as structured JSON containing the parsed name, address, and vehicle class.
Upload → parse → display: the full flow takes a single API call.

Why Bolt.new + StructOCR is a natural fit for Mobility Apps

Bolt.new generates and runs full-stack web applications directly in your browser. It handles the UI, components, and package management automatically — but securely extracting vehicle classes, addresses, and expiry dates from a driver's license is something you have to wire up yourself. StructOCR fills exactly that gap: one API call, structured JSON back. Tell Bolt what you want, paste in the fetch code below, and your driver onboarding flow is ready.

The problem: Standard AI fails on holograms and state layouts

Tools like Bolt.new are remarkable at generating apps instantly — but they stop at the file boundary. You can build a beautiful booking interface in minutes, yet the actual extraction of names, addresses, and vehicle classes from hundreds of different state and regional card layouts requires a dedicated Driver's License OCR API. Standard vision models routinely misread micro-print, hallucinate over security holograms, or fail to locate the right fields across chaotic layouts.

The solution: 50-state & global parsing, instantly

StructOCR's /v1/driver-license endpoint accepts a photo and returns a clean JSON object with the validated driver details. It automatically handles the chaotic variations of state IDs, decodes dates, and structures the address. Because it speaks plain HTTP, Bolt.new can wire it up from a single fetch call without heavy backend dependencies.

Integrate StructOCR in Bolt.new (3 Steps)

  1. Create a Bolt.new project and describe your app

    Open bolt.new and start a new prompt. Describe the mobility or verification tool you want to build — be specific about the fields you need.

    Try this prompt: "Build a mobile-friendly car rental onboarding app. Users can upload a photo of their driver's license, and the app will display the extracted full name, license number, address, and vehicle class."
  2. Tell Bolt to call the StructOCR API

    Once Bolt scaffolds the UI, paste the follow-up prompt below. Bolt will write the fetch call, handle the file upload, and wire the response to your UI components in its in-browser editor.

    Follow-up prompt: "When a user uploads an image, send it as a multipart/form-data POST to https://api.structocr.com/v1/driver-license with an Authorization header containing my API key. Display the returned JSON fields in the results panel."
    // Bolt generates something like this — you just supply the key in .env const response = await fetch('https://api.structocr.com/v1/driver-license', { method: 'POST', headers: { Authorization: `Bearer ${import.meta.env.VITE_STRUCTOCR_KEY}` }, body: formData, });
  3. Add your StructOCR API key to your environment

    In the Bolt.new file explorer, create or open the .env file to securely add your StructOCR key. The app will automatically reload with your live scanner.

    Variable name: VITE_STRUCTOCR_KEY — get your free key at structocr.com/dashboard
    VITE_STRUCTOCR_KEY=sk_live_xxxxxxxxxxxxxxxx

What you can build in Bolt.new with this integration

  • Car rental & sharing (Mobility): Let users snap a photo of their license to instantly populate booking forms and verify driving privileges. A core feature for mobility apps.
  • Delivery driver onboarding: Build a mobile portal where gig-economy contractors upload their licenses for instant identity verification and vehicle class checking.
  • Auto insurance quoting: Create a tool that scans a user's license to auto-fill their name, address, and DOB into a quoting engine, drastically reducing form abandonment.
  • Age verification for delivery: Add a quick scan step for drivers delivering alcohol or restricted goods to verify the recipient's age automatically based on the extracted `date_of_birth`.

The prompt and the code

Copy the follow-up prompt into your Bolt.new chat to generate the integration. The code block shows what Bolt typically produces — useful if you want to verify or tweak it.

Prerequisite: A free StructOCR account — get your API key at structocr.com/dashboard (no credit card required)

I need to add Driver's License OCR to this app.

When a user uploads an image:
1. Send it as multipart/form-data to: POST https://api.structocr.com/v1/driver-license
2. Include the header: Authorization: Bearer ${VITE_STRUCTOCR_KEY}
3. The response is JSON with fields: data.document_number, data.surname, data.given_names, data.address, data.vehicle_class, data.date_of_expiry
4. Display the extracted driver data in a clear, formatted profile card
5. Show a loading spinner while the request is in flight
6. Show an error message if the upload fails

Use the environment variable VITE_STRUCTOCR_KEY for the API key.

What the API returns

A comprehensive JSON object containing the parsed license fields. Your Bolt.new app can bind this directly to the UI components.

{
  "success": true,
  "data": {
    "type": "drivers_license",
    "country_code": "USA",
    "region": "CA",
    "document_number": "E3802489",
    "personal_number": null,
    "surname": "IDNOOB",
    "given_names": "MING",
    "date_of_birth": "1988-06-06",
    "date_of_expiry": "2020-06-06",
    "date_of_issue": "2015-07-22",
    "sex": "F",
    "address": "750 GONZALEZ DR APT 6B, SAN FRANCISCO, CA 94512",
    "vehicle_class": "C",
    "extra_details": {
      "fathers_name": null,
      "mothers_name": null,
      "rg_number": null,
      "card_security_number": "06/09/2014599A5/DOFD/19"
    }
  }
}

Technical Specs

  • Formats accepted: PNG, JPG, WEBP — optimized for smartphone and webcam photos
  • Response time: typically 1–2 seconds per license
  • Condition handling: robust against lamination glare, holographic overlays, and worn-out plastic
  • Data Privacy: Zero data retention architecture; images are processed in memory and immediately discarded
  • Coverage: Supports all 50 US States, Canada, UK, Australia, EU, and dozens of international layouts

Key Features

  • Address Structuring: automatically parses complex multi-line addresses into clean, readable strings
  • Format validation: automatically verifies document numbers and dates against regional logic
  • Multi-angle support: reads licenses held at skewed angles or taken in busy backgrounds
  • Vertical ID support: accurately reads both standard horizontal licenses and vertical under-21 layouts

Live Demo: Passport scanner

No registration required. Upload a file to test the extraction.

1
Upload
2
Results

Drop files here or click to browse

JPG · PNG · WebP  ·  up to 500 files · max 4.5 MB each

No files selected

Frequently Asked Questions

Does StructOCR work inside a Bolt.new app?

Yes. StructOCR is a standard REST API that accepts a file and returns JSON — Bolt.new can call it directly from a client-side fetch in its in-browser WebContainer environment.

Where should I store the API key in Bolt.new?

For testing within Bolt, you can create a `.env` file in the browser's file explorer and add `VITE_STRUCTOCR_KEY`. For production applications handling PII, we strongly recommend proxying the request through a secure backend to keep your API key private.

Does StructOCR store the driver's license photos?

No. StructOCR operates on a strict zero-data-retention policy. Images are processed in memory to extract the JSON data and are instantly discarded, ensuring GDPR and SOC2 compliance.

Can it read licenses from all 50 US States?

Yes. Our model is trained on the vast variations of layouts, fonts, and security features across all 50 US states, as well as major international regions.

How can I test the accuracy before building?

You can verify the model live using our free driver's license scanner tool.

Is there a free tier to test with?

Yes. StructOCR's free plan includes 10 scans per month with no credit card required. Check out our pricing page for full details.

More Tutorials

Precise Data Extraction and Seamless Integration with AI-powered OCR API.

Empower your solutions with automated data extraction by integrating best-in class StructOCR via API seamlessly.

No credit card required • Full API access included