For extracting crucial information from the drug manufacturing batch records, a unique and optimized AI-driven approach is presented in this research. The prime focus of this research is to extract crucial and desired information from the scanned PDF documents. The AI-driven platform is proficient in efficiently filling the pharmaceutical drug batch record information into a standard, pre-defined format in an Excel sheet. To achieve such proficiency, the Speech-to-Text conversion technique is employed. Also, the same is used for achieving higher accuracy in data extraction. Further, an Optical Character Recognition (OCR) technique is implemented for comparative assessment of the accuracy of the platform in terms of performance on the handwritten text fields of the documents.