Abstract: To achieve recognition of silent speech, especially of the non-audible murmur this development raises as a first step, the acquisition and transmission of vibration data from the sub vocal speech. Because of the stochastic characteristics of an audio signal in the time domain this is treated and analyzed in the complex frequency domain. To achieve the frequency analysis is implemented in this development a Fast Fourier Transform (FFT). The data acquired and transformed with FFT are transmitted via a Wi-Fi network to a computer for further analysis of signal and image processing through an application developed in C # language.