WHAT IS TEXT TO SPEECH?
Text-to-speech (TTS) technology is a form of speech synthesis. It converts text-based information into verbal output that closely resembles a natural voice. Let’s take a look at how TTS software works, and how it can be used in the contact centre to improve the customer experience.
HOW DOES TEXT TO SPEECH SOFTWARE WORK?
A TTS Engine converts written text into a phonemic representation. Phonemes are the smallest units of human speech. These pieces are then converted into waveforms that can be output as sound. When combined, these create spoken words, phrases and sentences.
Text-to-speech software providers offer synthesized voices that have personality and sound similar to a live person. These solutions model voice quality and overall rhythm and intonation, which produces a synthetic voice that sounds highly natural and is difficult to distinguish from actual voice recordings.
HOW IS TTS SOFTWARE USED IN THE CALL CENTER?
In the call center, TTS technology can be used to provide a personalized experience for customers, without requiring assistance from live agents. Typically utilized in tandem with an IVR system, text-to-speech can provide personalised information to callers. For example, TTS might “speak” information particular to that individual, such as greeting a customer by name, providing account information, confirming details – such as an order, payment, or appointment, or giving a special offer message.
While primarily thought of as an inbound customer service tool, text-to-speech software can also be used quite effectively for outbound programs. TTS allows companies to use “unattended outbound” or “broadcast” campaigns to deliver important customer information without using agent resources.
Text to Speech software may be used to look up and generate words from customer records in the contact centre’s database, or users may choose to pre-build phrases of static text into longer messaging, so that the static text may utilise the same voice as the text that is generated on the fly.
The best TTS software vendors provide a range of languages and accents, and a variety of female and male voices, so companies can provide an experience that matches their customer profiles or helps promote an image for their brand.
HOW IS TEXT-TO-SPEECH DIFFERENT FROM SPEECH-TO-TEXT SOFTWARE?
TTS creates spoken output from written inputs. Speech-to-Text captures verbal audio inputs and converts them into written words. Speech to text is also known as voice recognition or automated speech recognition (ASR). It is also commonly used with inbound contact centres and IVR systems to allow customers to speak responses to menu selections or questions, in order to determine how to route the caller for faster service. It can also be used to create transcripts of conversations for use with speech analytics applications, to allow companies greater insight into the customer experience.