AI Document Parser (AISAY) – An AI-Powered Document Reader and Transcription API Service | Singapore Government Developer Portal
Have feedback? Please

AISAY header banner

AISAY is an AI-powered document reader that can provide structured responses, extract, and integrate information from various documents into existing systems.

It can automatically detect, scan, and comprehend a variety of documents. This includes handwritten notes, printed articles, multilingual text, and structured/unstructured documents. Unlike traditional Optical Character Recognition (OCR) systems, AISAY can provide structured responses for documents such as images (JPEG, PNG, TFIF) and PDF files. For documents issued by local entities (businesses, governments, and institutions), AISAY can even fine-tune the documents prior to processing.

To determine if additional support is required for a given task, AISAY will also provide a confidence score per task. For instance, if the confidence level is high, the automation system can proceed with minimal human intervention. On the other hand, if the confidence level is low, the system may require human review or further verification.

AISAY supports the following document types, but other document types can be supported on request.

  • ID Documents such as NRIC/employment pass/S pass/work permit/dependent pass/long-term visit pass/student pass/driver’s license/11B or passports (machine-readable)
  • Agreements and contracts
  • Invoices/receipts/delivery orders
  • Bank statements

AISAY is scalable as it is hosted serverless on the cloud, so scaling in volume can be handled. It can cater for large file sizes due to its ability to run extraction processes asynchronously.

AISAY is under active development and is available for systems in production for processing documents, supporting security and data classification up to RESTRICTED/SENSITIVE NORMAL. Moving forward, more document types will be supported.

How It Works

AISAY accepts image files (JPEG, PNG, TIFF) or PDF documents and responds with a machine-readable, structured JSON response to extracted data.

AISAY uses Optical Character Recognition (OCR), Document Question-Answering (DQA) techniques alongside a Large-Language Model (LLM) to consider the location and content of text on a document in order to derive context and answer queries. AISAY also performs extensive pre-processing and post-processing of documents to ensure clean and accurate results.

AISAY is scalable with synchronous and asynchronous invocation options, which allow for the processing of large file sizes.

Key Benefits

  • Reduction of manual errors and improved data accuracy due to auto-filling of key data for form submission from document uploads. This makes form filing more effective and frees up users’ time for more productive tasks.
  • Improved digital service experience as key data can now be filled in automatically by AISAY once documents are uploaded.


Contact the product team using the form below for AISAY’s pricing information.

Contact Us

For further queries, email Nicholas, Lay Si, and Zhixun

Last updated 25 April 2024

Was this article useful?
Send this page via email
Share on Facebook
Share on Linkedin
Tweet this page