10.34848/NLZRDM William Ricardo Rodríguez0000-0002-6183-5779(Pontificia Universidad Javeriana)Oscar Julian Perdomo0000-0001-9493-2324(Universidad Nacional de Colombia)Martínez, Angela0000-0002-2358-4198(Universidad del Rosario) Universidad del Rosario 2025 doi:10.34848/NLZRDM/B5QIKAdoi:10.34848/NLZRDM/SYMKU0doi:10.34848/NLZRDM/Z76IEFdoi:10.34848/NLZRDM/XUSS8Qdoi:10.34848/NLZRDM/SPDUG9doi:10.34848/NLZRDM/VF9K6Adoi:10.34848/NLZRDM/8JCTDGdoi:10.34848/NLZRDM/OLVTWVdoi:10.34848/NLZRDM/IM45SBdoi:10.34848/NLZRDM/PUW0FWdoi:10.34848/NLZRDM/CUOSYLdoi:10.34848/NLZRDM/E53FXY EMOVOX is an AI-based algorithm designed to detect and analyze the five basic emotions — joy, sadness, anger, fear, and disgust — through voice. Using acoustic-prosodic features and machine learning models such as Decision Trees, Random Forest, and Support Vector Machines, EMOVOX identifies emotional biomarkers from more than 80 variables related to tone, intensity, and rhythm. This tool supports research and clinical assessment in mental health and communication sciences, offering an objective and interdisciplinary approach to understanding emotion through speech. Martínez, Angela(Universidad del Rosario)