Emotion-Driven Music Recommendation System Using Multimodal AI

Emotion plays a crucial role in influencing human preferences, particularly in music selection. This project presents an Emotion-Based Music Recommendation System that uses artificial intelligence to analyze a user’s emotional state and provide personalized music suggestions. The system supports text, voice, and video inputs, enabling multimodal emotion detection for improved accuracy. Text and voice inputs are processed using natural language processing and speech-to-text techniques (Whisper), while video inputs are analyzed using computer vision for facial emotion recognition. Based on the detected emotion, the system recommends suitable music tracks using Spotify and YouTube Music APIs. The application is developed using Streamlit, integrating deep learning models and external APIs to deliver an interactive and user-friendly experience. Overall, the system enhances personalization, user engagement, and emotional well-being, demonstrating the application of AI in affective computing and recommendation systems.