ElevenLabs has unveiled its Voice Design API, a tool that allows users to generate unique voices from prompts, according to ElevenLabs. This innovative feature enables the creation of voices with specific characteristics such as age, accent, and tone, or even fantastical voices resembling ogres, witches, and pirates.

API Features and Capabilities

The Voice Design API offers two primary endpoints. The first endpoint generates three unique voice previews based on a text prompt, providing users with a variety of options to choose from. The second endpoint allows users to save these voice previews to their library, offering flexibility and control over voice customization.

X to Voice Project

To showcase the potential of the Voice Design API, ElevenLabs developed the X to Voice project. This demo project creates a unique voice and avatar based on a user’s X (formerly Twitter) profile. By analyzing the user’s profile, the tool generates a personalized voice, demonstrating the API’s ability to integrate social media data into voice synthesis.

Open Source Contributions

ElevenLabs has also made the X to Voice project available as an open-source example. Developers can access the project on GitHub, allowing them to explore and expand upon the capabilities demonstrated in the demo. This move aims to foster innovation and encourage the development of new applications utilizing the Voice Design API.

The release of the Voice Design API marks a significant step forward in voice synthesis technology, offering developers and users alike the tools to create highly personalized and diverse voice outputs. With the added functionality of integrating social media profiles, the possibilities for application in various industries are vast and promising.

Image source: Shutterstock