​
Overview

The Voice Settings tab allows you to configure the voice and audio presentation of your AI Agent. This plays a critical role in shaping how your agent sounds and how natural the overall experience feels to the user.

​
Selecting a Voice Provider

You can choose from multiple voice providers that support a wide variety of synthetic voices. Once a provider is selected, a catalog of available voices is displayed for that provider.

​
Choosing a Voice

From the provider’s voice list, you can select the exact voice you want your AI Agent to use. Each voice has a different tone, cadence, and style—some are casual, others professional, some high-energy, and others calm and neutral. This allows you to tailor your agent’s tone to match the use case and brand.

You can also sample each voice before applying it to the agent, ensuring the final selection aligns with your expectations. Voices can be filtered by:

  • Language (e.g., English, Spanish, French)
  • Gender (e.g., male, female, neutral)
  • Use Case (e.g., professional, casual, support)

​
Background Sounds

You have the option to add background audio to the call, such as light office ambience. This small detail can significantly improve how natural the interaction feels, making it more relatable to users.

​
Input Minimum Characters

This setting determines the minimum number of characters a user must say or type before the AI begins processing a response. It can be used to filter out overly short or ambiguous utterances.

With these configurations, the Voice Settings tab gives you complete control over how your agent sounds and the auditory atmosphere it creates, contributing to a more engaging and personalized user experience.