Voice Design, launched as the first generative model for creating synthetic voices, allows users to build unique voices by selecting attributes such as gender, age, and accent, and introduces randomness to ensure each voice is distinct. This innovation is part of a broader effort to enhance AI storytelling tools for publishers and creators. By enabling users to design bespoke voices, Voice Design addresses the demand for specific speech characteristics without relying on a limited set of pre-recorded voices, offering applications in fields like book narration, news publishing, and gaming. Additionally, the voices are entirely artificial, providing exclusive voice options for various use cases. ElevenLabs plans to expand its offerings with features like Studio for narration editing and intonation editing support, further enhancing the capabilities for creating lifelike audio experiences.