đ¤ Seamlessly integrate cutting-edge AI chatbots and text-to-speech into your Unreal Engine projects!
Transform your games and applications with powerful AI conversation capabilities and high-quality voice synthesis using the most advanced language models and TTS services available today. This plugin provides direct access to OpenAI's GPT models, Anthropic's Claude, DeepSeek's advanced reasoning models, and premium text-to-speech services - all through simple Blueprint nodes!
Quick links:
đ Documentation
đŦ Discord support chat
đ Custom Development: solutions@georgy.dev (tailored solutions for teams & organizations)
⨠Key features:
Multiple AI Providers: Connect to OpenAI, Claude, and DeepSeek through their official APIs
Premium Text-to-Speech: High-quality voice synthesis with OpenAI TTS and ElevenLabs (including latest V3 models)
Latest Models Supported: Access cutting-edge models including GPT-4o, Claude 3.7 Sonnet, DeepSeek Reasoner, and ElevenLabs V3
Flexible Response Handling: Choose between complete responses or real-time streaming (chunk by chunk) for both chat and TTS
Streaming TTS: Real-time audio synthesis with minimal latency for dynamic voice experiences
Multilingual Support: ElevenLabs V3 supports 70+ languages with human-like expression
Blueprint Ready: Simple nodes for immediate integration without C++ coding
Cross-Platform: Works on all platforms supported by Unreal Engine (Windows, Android, Meta Quest, Mac, iOS, Linux, and more)
Easy Authentication: Simple API key management for all services
đ§ Supported models:
OpenAI Chat:
GPT-3.5 Turbo
GPT-4o
GPT-4o Mini
GPT-4-32k
GPT-4 Turbo
O1
O1 Mini
O3 Mini
Claude (Anthropic):
Claude 3.7 Sonnet
Claude 3.5 Sonnet
Claude 3.5 Haiku
Claude 3 Opus
DeepSeek:
DeepSeek Chat
DeepSeek Reasoner (with dedicated reasoning output)
OpenAI TTS:
Multiple premium voices (Alloy, Nova, Shimmer, Echo, Fable, Onyx, and more)
Regular and streaming modes for optimal performance
High-quality audio synthesis optimized for real-time use
ElevenLabs TTS:
Eleven V3 - Latest model with human-like expression (70+ languages)
Eleven TTV V3 - Advanced Text-to-Voice design model
Eleven Turbo V2.5 - High quality, low-latency with multilingual support
Eleven Flash V2.5 - Ultra-fast model for real-time applications
Multiple legacy models for compatibility and specific use cases
Regular and streaming modes with advanced voice customization
đĄ Perfect for:
Interactive NPCs with intelligent conversations and natural voices
In-game assistants and guides with multilingual support
Creative content generation with voice narration
Educational applications with AI tutoring and speech synthesis
AI-driven gameplay mechanics with audio feedback
Virtual companions with personality and expressive voices
Audiobook and narrative experiences with dynamic content
Real-time voice interaction systems
Note: API usage requires accounts with respective services (OpenAI, Anthropic, DeepSeek, ElevenLabs) and may involve usage costs from these providers.