Powered by AI, our API extracts key information on envelopes and packages

Process US mail faster with our state-of-the-art computer vision OCR


Powered computer vision and natural language processing AI models, the API achieves high performance on US Mail packages and envelopes. It even recognizes address change labels.

Seamless integration

No setup or retraining required. Integrate seamlessly our API in your environment using our back-end client libraries and go for production in no time.


Our OCR API works synchronously, with an average processing time of no more than 2 seconds.

US Mail OCR extracted fields

Transform any scan or photos of US Mail into usable data in your software

US mail letter with OCR

Sender Name

Capture who the mail is from. The Mail OCR API supports both typed and handwritten characters for this field.

Sender Address

Capture where the mail is being sent from and, in some instances, where it needs to be sent back.

Recipient Names

Extract multiple recipient names on the envelope in the instance there is more than one relevant individual in a household, department, or organization.

Recipient Address

Extract to whom the letter or package must be sent to. Both handwritten and typed addresses will be scanned.

Other Address

Find address change or update labels here.

Private Mailbox Number

List any relevant private mailbox (PMB) number – a secure, personal mail storage service offered by a private company.

What is US Mail OCR?

OCR stands for Optical Character Recognition. US Mail OCR refers to technology that transforms an image of a receipt or package into structured data. This technology can be distributed as a software for developers, on the cloud (API), or as a library, allowing them to build mail-scanning features in their applications and avoid manual data entry.

US mail scanning

While receipt OCR refers to extracting key information from receipts, mail scanning is the wider process that includes the capture of the envelope or package and the information extraction – specifically sender and receiver names and addresses. For now, the API is suitable only for US Mail, not other geographies.

Technologies behind US Mail OCR

Our US Mail OCR technologies combine Computer Vision (CV) and Natural Language Processing (NLP) to detect and recognize text inside images. Today, most of those technologies are based on machine learning or deep learning.

US Mail OCR vs OCR

When used alone, the acronym OCR traditionally refers to the generic problem of detecting and reading text in an image, independently of any context. When used with additional context such as Mail OCR, the term doesn't refer to generic text extraction but to extracting key information in a Mail image. This pattern can be extended to other document types.
Examples: Invoice OCR or Passport OCR.

Optical character recognition (OCR)

OCR refers to technologies capable of detecting and reading text from images or documents in order to transform them into machine-readable format.
More details in our blog.

Try out our US Mail OCR API

Try out our products for free. No commitment or credit card required. If you want a custom plan or have questions, we’d be happy to chat.

logo Mindee

Schedule a meeting with one of our experts

Please provide the following information so we can connect you to the right teammate.

Oops! Something went wrong while submitting the form.