Today, Internet is the best place to communicate and share information among the people throughout the world and gives an endless support of knowledge and entertainment. The main objective of Internet technology is to increase efficiency and decrease human effort. With the introduction of Internet of Things (IoT) in the last decade, we have been pushing for ubiquitous computing in all spheres of life. Physically challenged people are also using the Internet with the help of Speech commands (SC). The main objective of this paper is to minimize the effort and increase efficiency of the Voice recognition and IoT based secured automation, which is named as Raspberry pi and IoT based Speech automation (RASP-IoT-SA) technique. This RASP-IoT-SA system has only worked for authenticated users which improves the security in home and industrial automations. This RASP-IoT-SA system consists of four different Process such as secured speaker prediction, voice data transmission, web update and voice data Receiver processing. In this research work, Mel frequency Cepstral Coefficient (MFCC) technique is used for Feature Extraction (FE). Artificial neural network (ANN) technique is used for two different process such as, speaker prediction and speech data recognition (SR). The experimental result shows that the MFCC and ANN based technique provides better results in terms of accuracy, precision, false measure and recall. The RASP-IoT-SA technique delivers 99% of speech recognition accuracy, which was higher than the existing Speech automation technique.