MapTheVoice employs two methods for location capture: Live GPS and manual selection on the Map. It utilizes the smartphones speaker to record voice, with an AI agent transcribing it. Users can attach photos to locations and capture multiple points in one session. All files, including JSON, CSV, Audio File (m4a), and photos (png), are stored in the smartphones Files Application. The JSON file is Location-enabled in GeoJson format, readable by GIS applications like QGIS or ArcGIS. Tabular information includes textual data from voice transcription and references to voice recordings and photos. MapTheVoice can transcribe 16 Languages. The application can also be used with headphones. In order to enable all the features of the application, Access to Location, Camera, Speaker and Microphone are required.