The aim of this paper is to present feature extraction method of Gujarati isolated digit for speaker identification using MelFrequency Cepstral Coefficient (MFCC). The objective of MFCC is to extract features that are present in speech signal. That produces Mel-coefficients of speech data which helps in representing speaker specific characteristics, thus this technique is one of the best technique for feature extraction especially for automatic speech & speaker recognition system. This can offer better security than keypad input system at the ATM, cashless system, mobile password, etc. The proposed approach helps to implement the speaker identification system. Where dataset of Gujarati numeral (0 to 10) was recorded from different speakers from different age groups. This paper presents approach for extracting features from the speech signal of spoken words using the Mel-Scale Frequency Cepstral Coefficients. All this implementation is built in MATLAB environment. The result describes how it transform the input waveform into a sequence of acoustic feature vectors.