Voice Design

Voice Design allows you to quickly generate custom voice options based on a text description. This feature enables you to:

1. Provide a text prompt describing your desired voice characteristics
2. Receive three different voice samples matching your description
3. Select one of these samples to instantly create a new voice

This resource consists of two main endpoints:

• Generate voice candidates based on a text prompt
• Create a new voice from one of the generated candidates

Prerequisites

• A valid Resemble API token
• A clear description of the voice characteristics you want - see How to Prompt for more information

Voice Design Flow

The typical voice design process follows these steps:

1. Submit a text prompt describing your desired voice (e.g., "A middle-aged female with an Australian accent, friendly and approachable, like a knowledgeable tour guide")
2. Listen to the three voice samples returned
3. Choose your preferred sample and create a new voice from it