Vietnamese Invoice
AI Data Extraction
Extract structured data from Vietnamese VAT invoices with near-perfect accuracy. TurboLens handles diacritics, MoF-compliant formats, and e-invoice standards natively.
Sample Extraction Demo
See how TurboLens extracts structured data from Vietnamese invoice (hoa don) documents.
Input Document

Extracted JSON Output
{
"invoice_number": "HD-2025-001234", "invoice_date": "2025-03-15", "seller_name": "Cong ty TNHH Thuong Mai Phat Dat", "seller_tax_code": "0312345678", "buyer_name": "Cong ty Co Phan Xuat Nhap Khau Sai Gon", "buyer_tax_code": "0301234567", "total_before_vat": 45000000, "vat_rate": "10%", "vat_amount": 4500000, "total_amount": 49500000, "currency": "VND", "payment_method": "Chuyen khoan"}Extracted Fields
Key data fields extracted from invoice (hoa don) documents.
Invoice Number
invoice_numberUnique invoice identifier following MoF format
HD-2025-001234
Seller Tax Code
seller_tax_code10 or 13-digit Vietnamese tax identification number
0312345678
Buyer Name
buyer_nameFull legal entity name with Vietnamese diacritics
Cong ty Co Phan Xuat Nhap Khau Sai Gon
VAT Amount
vat_amountCalculated VAT based on Vietnamese tax rates (0%, 5%, 10%)
4,500,000 VND
Total Amount
total_amountFinal invoice amount including VAT
49,500,000 VND
Payment Method
payment_methodPayment type in Vietnamese (e.g., Chuyen khoan, Tien mat)
Chuyen khoan
Language & Region Details
Special Handling
- Vietnamese diacritical marks (dau) with 12 vowel variants
- Tone marks affecting character recognition accuracy
- Mixed Vietnamese-English content on international invoices
Key Features
Purpose-built capabilities for Vietnamese invoice (hoa don) processing.
Vietnamese Diacritics Engine
Purpose-built OCR model trained on Vietnamese script with all 12 vowel variants and 6 tone marks for near-perfect text recognition.
MoF Format Compliance
Automatically detects and parses Ministry of Finance compliant invoice formats including e-invoice (hoa don dien tu) standards.
Tax Code Validation
Built-in Vietnamese tax code validation with checksum verification for both 10-digit and 13-digit formats.
Multi-Currency Support
Handles VND and foreign currency amounts on international trade invoices with automatic currency detection.
ROI & Business Impact
Field Accuracy
Average extraction accuracy across Vietnamese invoice fields
Processing Speed
Average time to extract all fields from a single invoice
Batch Throughput
Invoices processed per hour in batch mode
Related Solutions
Frequently Asked Questions
Yes. TurboLens supports all Vietnamese e-invoice formats mandated by the Ministry of Finance, including XML-based e-invoices and PDF renditions from major providers like VNPT, Viettel, and MISA.
Our OCR engine is specifically trained on Vietnamese script with all 12 vowel variants and 6 tone marks. This includes proper handling of stacked diacritics (e.g., Vietnamese characters with both a base vowel modifier and a tone mark).
TurboLens validates both 10-digit (headquarters) and 13-digit (branch) Vietnamese tax identification numbers, including checksum verification to flag potentially invalid codes.
Yes. Many international trade invoices in Vietnam use mixed Vietnamese-English content. TurboLens seamlessly handles multilingual content within a single document.
Get Started Today
Try DocumentLens for free or contact us for an enterprise solution with dedicated support and custom integrations.
Need Enterprise Support?
Submit an inquiry below or email us at support@turbolens.io
