AI Text-to-Speech Overview

Yeastar P-Series Software Edition supports an AI-powered Text-to-Speech (TTS) feature, which can convert text into lifelike speech. With TTS, you can easily create greetings or audio prompts simply by entering text, eliminating the need to record or upload audio files manually.

Requirements

  • Firmware: 83.19.0.110 or later
  • Subscription: Enterprise Plan or Ultimate Plan

Highlights

Enhanced efficiency
Instantly create and update audio prompts by simply editing text, without the need of recording, greatly saving time and resources.
Multi-language support
Offer a variety of language options, which can generate speech in different languages to meet diverse user needs.
Personalized settings
Choose from multiple standard and neural voice profiles, and adjust audio settings and flexibly adjust audios to match your requirements.
Multiple scenarios
Apply TTS-generated audio in IVR, queues, ring groups, and more, enhancing various communication scenarios.

Configuration steps

To start using the AI-powered Text-to-Speech (TTS) feature, follow the steps below.
  1. Enable the AI Text-to-Speech feature

    Enable the AI-powered Text-to-Speech (TTS) feature with a single click. After the feature is enabled, you can generate audio files via TTS when setting up custom prompts or greetings.

    For more information, see Enable AI Text-to-Speech.

  2. Generate audio prompts using the AI Text-to-Speech feature

    Create audio prompts for specific features by entering your desired text content and customizing audio settings such as language, voice profile, speed, and volume to meet your requirements.

    For more information, see Generate Audio Prompts using AI Text-to-Speech.