ElevenLabs offers a Voice Design tool that generates entirely new, unique AI voices from a text description, allowing users to create a voice that does not yet exist without uploading any audio recordings.

Voice Design takes a natural language prompt describing desired vocal characteristics—such as gender, age, accent, and personality—and generates a new synthetic voice model as output. The tool is offered as a supplement to the Voice Library for cases where no existing voice matches a user's needs. The generated voices can be previewed and saved to a user's voice library for use in text-to-speech generation.