Cross-platform runtime plugins for real-time audio processing, voice recognition, speech synthesis, lip synchronization, on-device LLM inference, AI-powered interactions, and intelligent game localization, with full Blueprint and C++ support.
Advanced audio processing at runtime
Import, export, transcode, and manipulate audio files at runtime across all platforms. Supports MP3, WAV, FLAC, OGG and more.
Real-time lip synchronization
Create realistic real-time lip sync for MetaHuman characters using audio from any source, including microphone input. Also compatible with CC4, Genesis, ARKit, and more.
Cross-platform speech recognition
Quickly convert speech to text offline with cross-platform recognition powered by Whisper, supporting transcription and translation in over 95 languages.
Offline speech generation
Generate realistic speech from text locally and offline, with cross-platform support, featuring 900+ voices across 47 languages, no internet required.
On-device LLM inference
Run large language models entirely on-device using llama.cpp. Supports any GGUF model with token streaming, an editor model manager, and full Blueprint and C++ APIs across all platforms.
API-based AI chatbots
Integrate advanced AI chatbots and high-quality TTS via APIs from OpenAI, Claude, Ollama, DeepSeek, Gemini, Grok, ElevenLabs, Google Cloud, and Azure, supporting both text-to-text and text-to-speech workflows.
AI-powered game localization
Streamline game localization using AI-powered translation services. Supports OpenAI, Claude, DeepSeek, Google Gemini, and Ollama with seamless Localization Dashboard integration.
These plugins are designed to work together seamlessly, creating a complete ecosystem for audio, voice, AI interactions, and localization in Unreal Engine projects of any scale.
Looking for specific features or customizations for your Unreal Engine project? Custom development services are available to meet your studio's unique requirements.
