Project Gutenberg has converted approximately 5,000 book files into audiobooks using synthetic voice. Working in concert with MIT and Microsoft, the project aimed to refine producing machine-generated audio conversions at scale. The researchers write: “Our system uses new advances in neural text-to-speech, emotion recognition, custom voice cloning, and distributed computing to create engaging and lifelike audiobooks…. We believe that this work has the potential to greatly improve the accessibility and availability of audiobooks.” In a paper on the project, they explain: “Different audiobooks require different reading styles. Nonfiction works benefit from a clear and neutral voice while fictional works with […]
