Speech recognition is a technology that attempts to involve audio cues during interaction with machines, instead of being limited to just visual and touch interfaces. However, a keyboard and mouse input is an archaic method of interaction, adding on to the fact that voice control is seemingly more natural. This study aims to implement speech recognition as a form of machine control to perform simple commands in a virtual simulation process. The simulation system is an in-house developed augmented reality robotic work cell which includes a robot arm, a conveyer belt, a computer numerical control (CNC) machine, and a pellet. Issuing commands are performed via the Windows Speech Recognition software built from the Microsoft Speech Application Programming Interface (SAPI). This software is advantageous because it can be fairly accurate once trained properly, is easily modifiable by anyone regardless of the operator’s programming knowledge, and is free. A macros tool is used to support the additional features of the recognition software which includes directly programmable Extensible Markup Language (XML) codes.