In biometric authentication, traditional methods like RFID cards, PINs, or single-modal biometrics are susceptible to spoofing and unauthorized access. This paper proposes a novel biometric system that integrates face and voice recognition to enhance identity verification, combining facial and vocal characteristics for a more secure and reliable authentication process. Utilizing deep learning models trained on extensive datasets, the system extracts and matches unique facial and vocal features, significantly reducing fraudulent access while maintaining high accuracy in diverse real-world conditions. It is designed to handle variations in facial expressions, lighting conditions, background noise, and facial masks, ensuring robust verification even when masks are worn. By incorporating a facial mask dataset, the system effectively distinguishes between masked and unmasked faces, enhancing security and reliability. Additionally, the system is optimized for real-time processing, making it highly scalable and efficient for applications requiring fast and precise identity verification. The integration of face and voice recognition, along with the use of a facial mask dataset, improves both security and authentication speed, offering a comprehensive and sophisticated response to modern identity verification challenges. Experimental results demonstrate that this approach outperforms traditional single-modal biometric systems, reducing the risk of spoofing and ensuring high performance even in dynamic environments.