Text-to-Speech Conversion

Text-to-Speech (TTS) also known as speech synthesis is a process of converting text into a human-sounding voice. EnableX provides options to play TTS prompts in a gender-specific voice and various languages. You can provide the text dynamically depending on the situation and configure the prompt.

Benefits of TTS

  • Building an IVR or other voice applications without spending much time recording each prompt in a human voice. The ability to dynamically generate TTS prompts from raw text saves a lot of development time and effort.
  • Building Voice Bots powered with Artificial Intelligence that can communicate with users using TTS and understand user's speech using Automatic Speech Recognition.
  • Building applications for people with a learning disability, visual impairment, or literacy challenge thus providing equal access to information.

The input text for the prompt along with the voice and language selection can be passed to the New Call API for an inbound call as configured on the EnableX portal or to the Play command for IVR.

text : "", // Text to be played
voice : "male / female",
language : "" // language in which the TTS prompt
// is to be played