From the earliest mechanical synthesizers in the late 1800s to the advent of current virtual voices, each with its own distinct personality and style, speech synthesis has captivated researchers for generations. The end goal always being to produce syntheses that are indistinguishable from genuine human speech. The endeavor holds increasing importance in today’s world, spanning from supporting people with speech impairments to reinventing how information is communicated. In this study, we delve into a previously untapped area of linguistics: how sound profiles and pitch modulations differ from speaker to speaker. With the objective of enhancing the process of synthesis and offering more authentic and natural-sounding results, this paper serves as the first step in a marathon of innovation.