Comparison of synthetic voices produced in generative artificial intelligence technology with real voices

This research aims to identify the similarities and differences between synthetic voices produced using artificial intelligence technology and real human voices. Employing descriptive and comparative methodologies, the study examines the perceptions, naturalness, expressiveness, and reliability perceptions of synthetic and real voices. Participants have engaged in listening tests and semi-structured interviews to assess the differences between AI-generated synthetic voices and real human voices. The research also addresses the impact of synthetic voices on user experience and their social acceptance levels. The findings indicate that while technology provides advantages in sound production, human voices still surpass in areas such as emotional expression and natural sound quality. This study aims to illuminate the future development of synthetic voice technologies and provide scientific data that may help these voices gain broader acceptance and application.