Communication is a very important thing to establish social relations. In communicating, deaf and mute persons have difficulty conveying what information they want to convey. The Android-based Spoxtech application is an application specially designed for deaf and speech impaired persons. As the name implies, Spoxtech is taken from the word speech to text - text to speech. This application can make it easier for users to communicate because it is equipped with a voice menu that functions to detect the spoken voice which is then converted into text and a typed menu which functions to detect writing which is then converted into voice form. This application was created using the Hidden Markov Model algorithm in generating sound into text and using the finite state automata method in generating text into sound by performing two-level decapitation. This results of this study were carried out by testing the whitebox and blackbox. In this research, the text normalization test on the typewriter menu was also carried out, namely each word containing currency, time, temperature, and number units. The accuracy value obtained in testing this application uses Indonesian by testing the voice menu and typing menu and testing the two-level decapitation, the value is 100% of the 300 words in Indonesian.