Speech Generation System

Description

A fast, local neural multilanguage text-to-speech system that sounds great and is optimised for use with Unreal Engine.

Features:

• Converting text to speech in different languages (English, Deutsch, Spanish, Chinese and so on. 19+ languages);
  

• Ability to select different types of voices (47+ voices);
  

• It works offline, in real time;
  

• Easiness of integration.
  

Technical details

Code Modules:

•  SpeechGenerationSystem (Runtime)

Number of Blueprints: 0

Number of C++ Classes: 3

Network Replicated: No

Supported Development Platforms: Windows (x64)

Supported Target Build Platforms: Windows (x64)

The plugin uses Piper for speech generation (MIT licence).

The plugin uses fragments of code from the RuntimeAudioImporter plugin (MIT licence).