Riva Speech Synthesis
Release Version: 1.2.0
Release Date: May 6, 2024
Description
By using Riva Speech Synthesis (SS) plugin to UniMRCP Server, IVR platforms can utilize NVIDIA Riva Text to Speech API via the industry-standard Media Resource Control Protocol (MRCP) version 1 and 2.
NVIDIA Riva Text-to-Speech API performs text to speech conversion supporting the following main features.
Human Sounding Speech
The Riva TTS service is based on a two-stage pipeline, which forms a text-to-speech system that enables you to synthesize natural sounding speech.
Languages and Voices
The text to speech API supports a growing number of languages and voices.
Voice Output Parameters
By using SSML, the API allows to adjust pitch, rate, and pronunciation through phoneme.
Custom Model
Riva allows to build, train and deploy custom models.
Addon Packages
Solutions
IVR
platform
MRCP
server
- Riva Speech Synthesis
Solutions
IVR
platform
MRCP
server
- Riva Speech Synthesis
Documentation
This section provides references to installation, configuration and usage guides.
Installation
RPM Installation Manual
WIKIObtain and install the RPM packages for Red Hat / CentOS.
Deb Installation Manual
WIKIObtain and install the deb packages for Debian / Ubuntu.
Usage
Usage Manual
WIKILearn how to configure and use the plugin.
Supplimentary
Release Notes
WIKITrack down the changes introduced in each release.