The project named AEMTAVI (a Spanish acronym for Arquitectura Espacial Multilingüe de Traducción Automática de Video e Imagen), comes from the Latin and means “I got it”, and consists of a spatial system for the integration of voice and sign language that seeks to be an international communication standard in deep space. In other words, we are talking about algorithms for language learning. The general interest of this project is the participation in the assembly of communication elements, with the ease of operating with voice integration adapters and local translation adapters in the Moon Village, through the use of a multilingual neural machine translation system. These devices are space traffic agents that would provide two-way response communication in voice or non-auditory signal in front of audio and image receivers.