Voice-over anatomy lectures created by AI-voice cloning technology: a descriptive article

Abstract

The COVID-19 pandemic revealed the pivotal role of digital learning and online lecture videos, leading a shift toward blended and flipped classrooms in the post-pandemic era. This shift calls for development and (or) refreshment of novel online educational resources, such as Voice-Over PowerPoint (VOPPT) presentations, specifically designed for asynchronous or synchronous learning methods. However, resource limitations often impede the timely delivery of high-quality instructional materials. In this descriptive article, the use of AI-voice cloning technology to automate the creation of VOPPT presentation has been explored. Descripts' Overdub tool, an AI-voice cloning program, was trained on the 15-min voice sample of an anatomy professor, and the synthesized voice was used to narrate presentations on inguinal canal and extrahepatic biliary anatomy. The educational use of this novel approach was evaluated based on the second-year undergraduate medical students' qualitative feedback. Voice similarity analysis using Resemblyzer, an open-source Python tool, showed a high similarity score of 0.92 between the cloned and original voices. Despite this, students raised concerns about the robotic voice, quick pace, punctuation problems, pronunciation difficulties, and expressed reservations about AI-generated lecture narration. While the cloned voice closely matched the original, the AI-generated narration fell short of capturing the nuanced details needed for an effective anatomy instruction. This uncovers AI's current limitations in the educational contexts but establishes a foundation for future progress in AI-voice cloning technologies aimed at enhancing online educational resources for anatomy and medical education.