In this report we explain an alternative computational analysis to the detection diabetes Type 2 from voice, which is an end-to-end pipeline, the input to which is a speech file and the output is a prediction about its category(diseased or control), and it consists of 1) a feature extraction script to obtain richer representation of the speech signal (6000 parameters in placeof less than 20), and 2) learning and testing of a classification functionthat assigns a category to a new sample. The feature extraction can be usedtogether with the classical statistical analysis currently considered to be thegold standard in the literature on diabetes detection from voice.