Text To Speech (TTS)

Text-to-Speech or TTS is a technology that allows human speech to be reproduced artificially. This technology is capable of receiving a text and reproducing it with a synthesized artificial voice. It is an effective and innovative solution in the Contact Center environment since it helps automate many tasks as well as carry out novel integrations in terms of voice synthesis.

OMniLeads includes some algorithms that allow the extension of the Contact Center's functionalities through TTS engines.

Customized Audios and Text-To-Speech

Within the Resources -> Audios -> Customized Audios module, the creation of audio resources is allowed through files in the 16-bit wav format, or by facilitating their creation with Text-To-Speech (TTS) engines. These can then be used for IVRs, welcome audios, etc., depending on the business's telephone flow.

When you click on "Use TTS Service", the system allows the generation of audios using "text to speech" algorithms.

The "TTS Services" combo allows three text-to-speech engines to date:

Google TTS: Google Text to Speech Engine.

​ESPeak-NG: Open Source Multi-Language Synthesizer

​PicoTTS: TTS engine built in Python.

In turn, it allows combining these engines with predetermined voices with support in English, Spanish and Portuguese.

By typing the text to be converted into the Text Box of the view and pressing "Save", the engine selected in the "TTS Service" combo will take care of transforming the character string into a Synthesized Voice according to its predetermined algorithm.