AI-Powered OCR API for Brazilian Documents
From document to decision in seconds.
Send a birth certificate and get its data as structured JSON, ready for your system. No manual typing.
"""Your first call: extract the hosted sample certificate (fictitious data).
Needs the requests package and DOCSOCR_API_KEY in the environment.
"""
import os
import uuid
import requests
response = requests.post(
"https://api.docsocr.com/api/v1/documents/birth-certificate",
headers={"Authorization": f"Bearer {os.environ['DOCSOCR_API_KEY']}"},
json={
"imageType": "url",
"imageUrl": "https://docsocr.com/samples/certidao-nascimento-exemplo.jpg",
"requestId": str(uuid.uuid4()), # one id per document
},
timeout=120, # above the API's 90 s extraction budget
)
answer = response.json()
if response.status_code != 201 or not answer["success"]:
raise SystemExit(f"{response.status_code} {answer.get('errorCode', '')} {answer.get('message') or answer.get('error')}")
print(answer["data"]["dados_pessoais"]["nome_completo"])The Real Cost of Processing Documents Manually
Every minute your team spends fixing OCR errors is money thrown away. It's not just operational, it's strategic.
Manual Typing Is Expensive
Hours of your team's time copying document data into the system, with errors along the way.
Speed That Kills
Every certificate typed by hand delays your customer's onboarding and service.
Typing Errors
One wrong digit in a CPF or registration number means rework and a rejected record.
DocsOCR vs Traditional
OCR with AI That Works. No Excuses.
We process documents the way it should be: fast, accurate, and friction-free.
Automatic Fallback
Three AI engines: when one cannot answer, the next one takes over automatically.
- No manual intervention
- No charge if no engine answers
Built for Certificates
Extracts the fields of the Brazilian birth certificate, in the official model, as structured JSON.
- One API call
- No rules to configure
Pay Only for Data
You pay for extractions that return data. A refused image or an engine failure is not charged.
- No required subscription
- Free credits to start
Simple, Transparent Pricing
Start free, scale as you grow
Starter
For small teams getting started
PLAN CREDITS
- Monthly Credits1K
- Extra credit$0.04/credit
BURST PROTECTION
- RPM5
- Hourly50
- Daily350
FEATURES
- API access
- Usage dashboard
- E-mail support
Pro
For growing businesses with higher volume
PLAN CREDITS
- Monthly Credits4.5K
- Extra credit$0.03/credit
BURST PROTECTION
- RPM10
- Hourly150
- Daily1.5K
FEATURES
- API access
- Usage dashboard
- E-mail support
Business
For teams with high volume
PLAN CREDITS
- Monthly Credits14K
- Extra credit$0.02/credit
BURST PROTECTION
- RPM20
- Hourly450
- Daily4.7K
FEATURES
- API access
- Usage dashboard
- E-mail support
Why DocsOCR
Built for teams who need document processing that just works
Purpose-Built for Brazilian Birth Certificates
Extraction built for the official model of the Brazilian birth certificate.
All-Inclusive Pricing
Three AI engines, fallback and structured output — all included.
Single API Call
From document to structured JSON in one request.
AI Engine Fallback
When one AI engine cannot answer, the next one takes over automatically.
From Document to Structured Data in 3 Steps
Upload (API or Dashboard)
PDF*, JPG, PNG, WebP or GIF. Up to 10 MB, 1344 to 2048 px on the long side. Any channel, any time.
*Only the first page of a PDF is read.
AI Reads the Certificate
The AI engines read the image; if one fails, the next one takes over.
Receive Clean Data
Structured JSON ready to inject into your database or workflow.
{
"success": true,
"processingTimeMs": 6120,
"data": {
"documento": {
"tipo": "Certidão de Nascimento",
"órgão_emissor": "CARTÓRIO DO 1º OFÍCIO DE REGISTRO CIVIL DE RECIFE - PE"
},
"dados_pessoais": {
"nome_completo": "ANA BEATRIZ DOS SANTOS TESTE",
"data_nascimento": {
"texto_completo": "",
"dia": "15",
"mês": "03",
"ano": "2020"
}
}
}
}Numbers That Matter
Frequently Asked Questions
Everything you need to know about DocsOCR
What is DocsOCR?
DocsOCR is an AI-powered OCR API specialized in extracting structured data from Brazilian documents. It turns scanned documents into clean, structured JSON data ready for your systems.
What documents are supported?
Currently, DocsOCR specializes in Brazilian birth certificates (certidões de nascimento), with full field extraction including names, dates, registration numbers, and issuing office details. More document types are being added.
How does the OCR extraction work?
You send a document image via our REST API (PDF*, JPG, PNG, WebP or GIF). Our AI engines read the certificate, extract its fields and return structured JSON in seconds. *Only the first page of a PDF is read.
How accurate is the extraction?
Accuracy depends on the image quality and the document's condition: that is why our standard takes images of 1344 to 2048 px on the long side, where extraction reads best. If one AI engine fails on a document, another processes it automatically. We recommend testing with your own documents.
How does the AI fallback work?
DocsOCR has three AI engines: fast, mini and large. By default a request goes to the standard engines, mini and large, and if one fails, the next one answers automatically — no manual intervention needed. A request can also ask for the fast engine, which is tried first, with the standard engines behind it. If no engine can answer, the answer comes back as 201 with success: false and an errorCode, at no charge: send it again later.
What file formats and sizes are accepted?
We accept PDF*, JPG, PNG, WebP and GIF files, up to 10 MB per document. You can send files via URL or Base64-encoded content in the API request. Our image standard is 1344 to 2048 px on the long side (for an A4 scan, about 120 to 175 DPI), where extraction reads best: an image outside it is refused at no charge, or resized on our side for 1 extra credit when the request sets resizeImage: true, which adds a little time to the answer. *Only the first page of a PDF is read.
How much does DocsOCR cost?
DocsOCR uses a pay-as-you-go credit system. Each extraction that returns data costs 1 credit on the standard engines. A request can ask for the fast engine instead: it costs 1.8 credits when it answers, and if fast cannot answer, a standard engine answers for 1 credit. A refused request, or one that no engine could serve, is free. New accounts receive free credits to get started — no credit card required.
How do I get started with the API?
Create a free account, generate an API key from the dashboard, and make your first API call. Check our interactive API documentation for code examples in multiple languages.
Is my data secure?
Yes. DocsOCR is 100% compliant with LGPD (Brazilian data protection law), GDPR, and CCPA. Document images are processed in real time and are not stored after extraction. Communication uses TLS 1.2 or 1.3, and stored data is encrypted at rest.
Can I test before committing to a plan?
Absolutely. Every new account receives free credits to test the API with real documents. No credit card is required to sign up, and you can upgrade to a paid plan whenever you're ready.
Ready to eliminate human error?
Start today with 50 free credits. No commitment, no card, just cutting-edge technology.
Refused images and engine failures are not charged.