Voice Savior is a tower defense game that allows the players to control the game with voice commands only. The main research goal for this project is to investigate how speech recognition can be used in games. There will be two types of control methods in the game, which are voice-only control and combination of voice commands and mouse control. To implement a speech recognition into a game, I will use the Speech Application Programming Interface (SAPI) developed by Microsoft, and the Unity engine will be used to develop the game. Specifically, the KeywordRecognizer will be used to build the speech recognition for the game. A user case study will be held to investigate the advantages and disadvantages of using voice control in games. The results of the study show that the combination of voice commands and mouse control can improve players’ performance in games.