Skip to main content

Elys GenAI Framework

Local, offline, real-time GenAI features for Unreal Engine 5

🎤STT

Speech-to-Text

Convert player voice to text in real-time using Whisper.cpp. Supports multiple languages, voice activity detection, and push-to-talk.

🧠LLM

Large Language Models

Power NPC dialogue with Phi-3-mini via llama.cpp. Dynamic conversations, streaming responses, and context management.

🔊Audio

Audio Capture

Robust microphone capture with consumer pattern. Push-to-talk, voice activity detection, and efficient ring buffers.

🔒Core

100% Offline

No cloud dependencies, no API keys, no subscriptions. All processing happens locally on the player's machine.

🌐Core

Multiplayer-Safe

Client-side processing with text-only replication. Never send audio over the network - only transcribed results.

📦Core

Blueprint-Friendly

Clean Blueprint API with events and async nodes. Full C++ access for advanced users who need it.

🏗️ Modular Architecture

Four focused modules with clean dependencies

🎯

ElysGenAICore

Foundation with interfaces, types, and settings. The base that all other modules depend on.

Interfaces • Types • Settings
🔊

ElysGenAIAudio

Microphone capture with ring buffers and consumer pattern for efficient audio distribution.

Capture • PTT • Ring Buffer
🎤

ElysGenAISTT

Speech-to-text with Whisper.cpp backend. VAD, streaming, and multi-language support.

Whisper • VAD • Streaming
🧠

ElysGenAILLM

Language model inference with llama.cpp. Conversation context and streaming generation.

llama.cpp • Phi-3 • Streaming