Runtime Text To Speech is an Unreal Engine plugin that brings offline, cross-platform, multilingual text-to-speech synthesis to your projects, powered by Piper, Kokoro, and ONNX Runtime. It supports 51 languages and 2800+ voices, runs entirely on-device with no internet required, and works on all platforms supported by Unreal Engine (UE 4.27 and newer). The video below walks through the setup process and demonstrates how to download voice models, synthesize speech at runtime using the streaming approach, and explore the included demo project.
Links:
Fab: https://www.fab.com/listings/0dab646f-73b4-46d9-bb7e-8e6c12bdd808
Documentation: Overview | Georgy Dev Docs
Windows demo: Redirect
Discord: Redirect
https://dev.epicgames.com/community/learning/tutorials/pYOl/fab-high-quality-offline-text-to-speech-in-unreal-engine-piper-kokoro