This research aims to develop a system capable of processing voice input to recognize Al-Quran reading by recitation of Tajwid, using wavelet signal extraction and classification of Tajwid rules using ANFIS. The process stages include data acquisition, audio data pre-processing, extraction using wavelet packets, division of training data and test data, and classification. The data obtained were 20 observations from 10 observations carried out in data pre-processing. The wavelet decomposition process produces six main features as ANFIS input variables and 64 rules. Then the data was separated into 17 observations for training data and three for testing data. The test results obtained from the training that had been carried out produced plots that were too fit; in this experiment, the WPANFIS classification model got 100% appropriate classification and SSE values that were the same as the training result, 0.00081225.