Smart Cities must be capable of "listening" to the city soundscape in real-time. The task of capturing, localization, and identification of the sound events that happening in the city is of vital importance for reducing response times to serious incidents and for city management. Processing information from sound can provide considerable savings with human resources and equipment while improving significantly the security of smart cities. Applications include noise monitoring near sensible locations and locating events such as, for example, traffic accidents, people in-distress and gun-shots. FI-Sonic, by means of its Smart Sound Stations (S3) and platform, provides intelligent audio processing and analytics for creating dynamic real-time noise and sound event maps, with the capability of localizing and identifying a number of different sound events. This location and identification features can also complement the public video surveillance installations. Therefore, FI-Sonic is combining the existing S3 units with 360 video cameras to create an integrated affordable price audio and video monitoring system of the city. The information gathered (sound with associated semantics, and video) can be used to oversee and support decision making process in near-real-time on a centralized control room and/or automatically inform the populations and other stakeholders.