Watson Speech Synthesis
Release Version: 1.6.2
Release Date: Jun 3, 2022
Description
By using Watson Speech Synthesis (SS) plugin to UniMRCP Server, IVR platforms can utilize IBM Watson Text to Speech API via the industry-standard Media Resource Control Protocol (MRCP) version 1 and 2.
IBM Watson Text to Speech API performs text to speech conversion supporting the following main features.
Human Sounding Speech
Text is instantly synthesized into human-sounding speech and can be used for real-time conversion.
Languages
The text to speech API supports a variety of languages.
Voice Output Parameters
By supporting SSML 1.0, the API allows changing certain characteristics of generated voice output like speaking rate, volume and pronunciation.
Voices
The text to speech API supports a variety of different male and female voices.
Addon Packages
Solutions
IVR
platform
MRCP
server
- Watson Speech Synthesis
Solutions
IVR
platform
MRCP
server
- Watson Speech Synthesis
Documentation
This section provides references to installation, configuration and usage guides.
Installation
Usage
Supplimentary
Release Notes
WIKITrack down the changes introduced in each release.