The main topic of this paper is the presentation of an indoor acoustic environment monitoring system for a robotic platform through a graphical user interface. The acoustic event is recognized by the joint use of six different models. The final decision is based on the predominant result. The effectiveness of each model is validated by the averaged performance metrics derived by a 5-fold cross-validation repeated 20 times. The values for the following metrics: averaged accuracy, macro-averaged precision, macro-averaged recall, and macro-averaged F1-score are all above 95% during the test phase. In addition to being displayed on the graphical user interface, the detected event is also converted into speech, and based on some pre-learned rules, the robotic platform can select the necessary task. A person in charge of daily monitoring receives an email notification from the robotic platform, called OMNI-Z, for each event that is considered a regular action. When an event is identified as potentially alarming, such as coughing or the need for certain types of medication, OMNI-Z decides to send an alert email to both the caretaker and the person who needs to intervene. Mel Frequency Cepstral Coefficients are used as features, and k-Nearest Neighbors, Linear Discriminant Analysis and Support Vector Machines are used as classifiers.