This paper aims to demonstrate concisely how we can promote voice bots for mental disease prediction and treatment recommendations. As a result of creating awareness among users, we will be able to provide proper medical solutions to prevent diseases. A preliminary training model and a study report were created to improve human interaction with databases. We describe the voice bots behavior and characteristics using natural language processing. Our paper proposes a deep feedforward multilayer perceptron-based AI Voicebot interaction and prediction model. During our analysis, we identified a knowledge gap regarding theoretical guidelines and practical recommendations for creating voice bots for lifestyle improvement programs. Throughout this paper, a brief comparison of our proposed model concerning the time complexity and accuracy of the tests is also discussed. During this study, we present a detailed overview of the functionalities and possible applications of voice bots. We also explore the accompanying challenges posed by their use, especially in health crises where these emerging technologies can prove to be highly beneficial. The findings of our study will help researchers to get a better understanding of the layout and applications of these revolutionary technologies. This will be necessary to continue improving voice bots in terms of their functionality and will be useful in preventing mental illness in the future.