Skip to content
Cloud Voice Documentation

AI Text-to-Speech Overview

Cloud Voice includes an AI Text-to-Speech (TTS) feature that converts written text into natural, lifelike speech. Instead of recording clips yourself or uploading prepared audio, you type the wording you want and Cloud Voice produces the audio for you, making greetings and prompts quick to create and just as quick to change.

Requirements

Section titled “Requirements”

Before you use AI Text-to-Speech, confirm the following:

  • Firmware: version 84.22.0.138 or later.
  • Subscription: an Enterprise Plan or Ultimate Plan.

What it offers

Section titled “What it offers”
  • Faster prompt updates: Because prompts start as text, you can create or revise them by editing a few words rather than re-recording, which saves both time and effort.
  • Multiple languages: Generate speech in a range of languages so your prompts suit the audiences you serve.
  • Customizable output: Pick from several standard and neural voice profiles and fine-tune settings such as speed and volume to match how you want the audio to sound.
  • Broad coverage: Use TTS-generated audio across features like IVR (Interactive Voice Response, the automated “press 1 for sales” menus) menus, queues, and ring groups to shape a variety of call scenarios.

How to get started

Section titled “How to get started”

There are two steps to putting AI Text-to-Speech to work.

  1. Turn on AI Text-to-Speech. Enabling the feature takes a single click. Once it is on, you can generate audio through TTS and assign those files as greetings or prompts for inbound calls, giving callers a more dynamic and personalized experience. For the procedure, see Enable AI Text-to-Speech.

  2. Generate your audio prompts. Build prompts for a specific feature by entering the text you want and adjusting settings such as language, voice profile, speed, and volume. For the full walkthrough, see Generate Audio Prompts using AI Text-to-Speech.