This paper introduces a system specifically designed for natural language to SQL translation. Leveraging the power of machine learning, the system incorporates deep learning models, namely RAT-SQL and RoBERTa, to improve the accuracy and effectiveness of the translation process. The paper provides an in-depth overview of the system's highlevel design, including using RAT-SQL as the core model and integrating the BERT approach for enhanced performance. It also discusses the dataset employed during the system's development and presents the results and conclusions. By utilising the synergy of RAT-SQL and RoBERTa, the system demonstrates promising advancements in the natural language to SQL translation domain, showcasing its potential to simplify and streamline the interaction between human language and structured database queries.