Researchers have developed an automated method using synthetic text-to-speech technology to create audiobooks, making them more accessible to users. They scanned classic literature and public domain texts from Project Gutenberg, including works by Shakespeare, Agatha Christie, and more. The open-source collection is available on platforms like Internet Archive, Spotify, Apple Podcasts, and Google Podcasts.
Traditional audiobook production can be time-consuming and expensive, but this automated approach offers a cost-effective and efficient solution. Researchers addressed challenges such as parsing digital books, handling formatting, and ensuring natural-sounding speech. Users can even generate audiobooks with their own voice using the technology.