A project to classify emotions like happiness, sadness, and anger from speech using MFCCs, machine learning models, and visualizations for audio features and model performance.

Speech emotion recognition system trained on multiple public datasets (RAVDESS, CREMA‑D, TESS, MELD, etc.). Uses audio features and deep learning to classify emotions (anger, happy, sad, neutral, fear, etc.) for more robust and generalizable models.

PyVoiceMood is an interactive voice-based assistant that ONLY detects the emotional sentiment of spoken input and prints the result.