Audiobooks have become an integral part of our literary world, with human voices typically guiding us through captivating tales. However, the rapid advancement of speech synthesis technology has opened the door to artificial voices. The question arises: do listeners engage with stories differently when narrated by a human or a synthetic voice? A recent study by Dr. Emma Rodero and Dr.Ignacio Lucas (IDIBELL) explores this very query, offering intriguing insights into our cognitive response to these two storytelling mediums.

The research aimed to compare how listeners perceive, visualize, and emotionally connect with stories when delivered by human and synthetic voices. The study assessed various aspects, including narrative engagement, physiological responses, and the retention of information.

The results painted a clear picture. Listeners expressed a strong preference for stories narrated by human voices. They revealed higher levels of engagement, more vivid mental imagery, increased attention, a more positive emotional response, and improved information retention when listening to human narrators.

While speech synthesis technology has made significant strides, there remain substantial disparities compared to human voices. As a result, employing synthetic voices for extended storytelling formats, like audiobooks, still presents challenges. This research underscores the enduring appeal of the human touch in the art of storytelling.

Reference:

Rodero E, Lucas I. Synthetic versus human voices in audiobooks: the human emotional intimacy effect. New Media Soc. 2021. 31 p. DOI: 10.1177/14614448211024142