The rapid advancement of facial recognition technology opens new frontiers for the development of music recommendation systems. The new approaches toward recommending music fail to bring in the effective integration of the emotional dimensions of music with the user’s personality and mood, this research paper presents a novel framework of a facial recognition-based music recommendation system that converges toward this objective. It enhances the musical experience for users through their suggestions because of higher resonance with emotional needs and preferences. This groundbreaking innovation includes facial recognition technology in the music recommendation systems. Subsequently, these emotional cues in combination with the analysis of musical features determine songs to be communicated to the listener for maximum resonance with his/her emotional state. Considering the dynamic emotive preferences from the user side, the system may decide to recommend songs to the user that is not only aligned with their past listening history but also cater to the user’s fluctuating emotional needs. This approach is quite different from traditional music recommendation systems that rely heavily on collaborative filtering or popularity-based algorithms. The system might change the face of how humans would interact and find music. It harnesses the power of deep learning and integrates multiple forms of data, it begins by collecting and extracting facial data using the FER dataset. Meanwhile, Song data is extracted from Spotify’s Web API, which allows facial and emotional data to be matched to specific song characteristics. Data cleaning and preprocessing are important steps in refining datasets and organizing them for efficient access. It leverages CNN’s unique ability to recognize and categorize emotional states expressed in facial images to guarantee ideal performance. The research has shown the possibility of computationally modeling the latent constructs underlying music listening and emotion regulation as well as identifying the relationship between user emotions musical mood and personality characteristics of each individual.