Tired of tracking a new AI model launch every day? Say no more. GenAI for Unreal is the definitive, production-ready plugin that handles the integration layer for you. Focus on your gameplay, while we provide a stable, unified, and powerful interface to the world's leading AI models. The plugin supports all current cutting edge LLM APIs like OpenAI's ChatGPT including the latest GPT-5.4, GPT-5.3 Codex, GPT-5.2, Anthropic's Claude Opus/Sonnet 4.6, Google's Gemini 3.1 / Nano Banana 2, XAI's Grok 4.1/4/3, DeepSeek's R1, Inworld AI TTS, and more. Plus, with OpenAI Compatible Mode, seamlessly switch to Alibaba Qwen, Mistral, Groq, OpenRouter, Meta Llama, BigModel GLM-4, or even run local models via Ollama for ultimate flexibility and cost-efficiency.

Now with GPT-5.4, Claude 4.6, Gemini 3.1, Inworld AI TTS, Function Calling, and OpenAI Responses API!! 🎉

View on Fab.com Product Documentation

What's New in v2.0.1!

This release is packed with major new features, integrations, and critical fixes:

• 🌐 Inworld AI Integration: Full support for Inworld Text-to-Speech, including standard and real-time streaming endpoints.
• 🔗 OpenAI Responses API (Beta): Integrated the new GenOAIResponses class to support OpenAI's structured Responses API.
• 🛠️ Function Calling (Tool Use): Added tool/function calling support for Anthropic Claude and OpenAI Chat models.
• 🧠 New Models: Anthropic Claude 4.6 Opus & Sonnet, OpenAI GPT-5.4/5.3 Codex/Image-1.5, Google Gemini 3.1 Pro/Flash Lite/Flash Image Preview, ElevenLabs Scribe V2 & V2 Realtime, and Inworld TTS 1.5 Max/Mini/1.

Key Features:

• Real-time Text Streaming: ⚡️
  Bring your characters to life with dynamic, real-time responses. Our streaming support delivers text in chunks as it's generated, perfect for creating live-narrated dialogue, responsive AI companions, and interactive storytelling without the wait.

• Advanced Chat Completions: 🤖
  Power your game with dynamic NPC dialogue, procedural quest generation, and real-time narrative adaptation using models from OpenAI, Anthropic, Google, XAI, and DeepSeek.

• Reasoning Models: 🧠
  Leverage the unique "think before you speak" capabilities of models like DeepSeek's R1 and XAI's Grok to generate core narrative components and complex logical outputs.

• Multi-Modal Vision/Text Input: 📸
  Allow models to "see" your game. Provide screenshots or other images as direct input along with text—now with support for Google Gemini! Perfect for creating AI-powered spectator commentary, dynamic player guides, or environment-aware NPC interactions.

• Image Editing: 🎨
  Go beyond generation. Edit existing images with powerful AI-driven tools to iterate on your visual concepts directly within the engine.

• Structured JSON Output: ❤️‍🔥
  Reliably get complex JSON responses from any supported model. For example, generating JSON for 100 AI-generated NPCs, each with their own unique stories, race, gender, and name.

• High-Quality Image Generation: 🖼️
  Integrate state-of-the-art image generation directly in your workflow with support for OpenAI's DALL-E 2, DALL-E 3, and GPT-Image-1 models.

• Text To Speech (TTS): 🔊
  Generate dynamic, high-quality voice lines for in-game dialogue, narration, or live conversations with AI characters using OpenAI's and ElevenLabs' TTS models.

• Function Calling (Tool Use): 🔧
  Enable AI models to call your game functions directly. Supported for Anthropic Claude and OpenAI Chat models, allowing AI-driven gameplay actions, data lookups, and dynamic world interactions.

• OpenAI Responses API: 📋
  Access OpenAI's new structured Responses API for more powerful and controlled model outputs, with full Blueprint and C++ support.

• Sound Effect Generation: 🎶
  Generate custom sound effects from text prompts using ElevenLabs' state-of-the-art audio models.

• Audio Transcriptions: 📝
  Power in-game voice commands or create interactive conversations by converting player speech to text with OpenAI's Whisper, GPT-4o, and ElevenLabs' transcription models.

• Effortless Server Proxying: ☁️
  Need to route requests through your own backend for security or custom logic? Our server proxy feature allows you to override API endpoints for any provider with a single setting, giving you complete control over your data flow.

• OpenAI Compatible Mode: 🔄
  Unlock incredible flexibility with support for Alibaba Qwen, Mistral, Groq, OpenRouter, Meta Llama, BigModel GLM-4, and local models via Ollama. Switch providers seamlessly without code changes for cost savings, privacy, or offline capabilities.

• Secure & Centralized Authentication: 🔐
  Manage all your API keys in one secure, centralized settings panel. Our system uses a non-portable, encrypted file to keep your keys safe and separate from your source control.

• Blueprint & C++ Ready: 🔗
  Enjoy simple, powerful Blueprint nodes for rapid iteration, and access the same robust, self-managing functions in C++ for maximum performance and control.

• Designed for Cross-Platform: 🌐
  The plugin exclusively uses standard, high-level Unreal Engine modules for networking and file management, ensuring it works on all platforms supported by the engine.

Available Integrations & Models

Disclaimer

This plugin requires an active API key from at least one of the supported AI providers to function. Please see our documentation for more information on how to obtain API keys.

A clean, unified API for the best models available today.

• OpenAI:
  • Chat: gpt-5.2, gpt-5.1, gpt-5, gpt-5-mini, gpt-5-nano, gpt-4.1, gpt-4o, gpt-4.1-mini, gpt-4.1-nano, gpt-4o-mini.
  • Responses API: gpt-5.4, gpt-5.4-pro, gpt-5.2, gpt-5.2-pro, gpt-5.3-codex, gpt-5.2-codex, gpt-5.1-codex-max, gpt-5-codex-mini.
  • Reasoning Models: o4-mini, o3, o3-pro, o3-mini, o1, o1-pro.
  • Image Generation: gpt-image-1.5, gpt-image-1, gpt-image-1-mini, dall-e-3, dall-e-2.
  • Audio TTS: gpt-4o-mini-tts, tts-1, tts-1-hd.
  • Audio Transcription: gpt-4o-transcribe, gpt-4o-mini-transcribe, whisper-1.
  • Structured Output (JSON Mode) ✔
  • Function Calling (Tool Use) ✔
  • Text and Audio Streaming ✔
  • Multimodal Chat ✔
  • Realtime API: gpt-realtime, gpt-realtime-mini.
• Anthropic:
  • Chat: claude-opus-4-6, claude-sonnet-4-6, claude-opus-4.5, claude-sonnet-4.5, claude-haiku-4.5, claude-opus-4.1, claude-opus-4, claude-sonnet-4, claude-3-7-sonnet, claude-3-5-sonnet, claude-3-5-haiku, claude-3-haiku, claude-3-opus.
  • Multimodal Chat ✔
  • Function Calling (Tool Use) ✔
  • Extended Thinking ✔ (Claude 4.5+)
• XAI:
  • Chat: grok-4-fast-non-reasoning, grok-4-fast-reasoning, grok-4-1-fast-reasoning, grok-4-1-fast-non-reasoning, grok-4.1, grok-4, grok-4-eu, grok-code-fast-1, grok-3, grok-3-mini, grok-3-fast, grok-3-mini-fast, grok-2-vision-1212, grok-2-1212.
  • Reasoning Models: grok-4-fast-reasoning, grok-4-1-fast-reasoning, grok-4.1, grok-4, grok-3-mini, grok-3-mini-fast.
  • Text Streaming ✔
  • Multimodal Chat ✔
• Google Gemini:
  • Chat: Gemini 3.1 Pro Preview, Gemini 3.1 Flash Lite Preview, Gemini 3 Pro Preview, Gemini 3 Flash Preview, Gemini 2.5 Flash, Gemini 2.5 Flash Lite, Gemini 2.5 Pro.
  • Reasoning Models: Gemini 2.5 Flash, Gemini 2.5 Pro.
  • Audio TTS: gemini-2.5-flash-preview-tts, gemini-2.5-pro-preview-tts.
  • Audio Transcription: Gemini 3.1 Pro Preview, Gemini 3.1 Flash Lite Preview, Gemini 3 Pro Preview, Gemini 3 Flash Preview, Gemini 2.5 Flash, Gemini 2.5 Pro.
  • Text Streaming ✔
  • Multimodal Chat ✔
  • Realtime: gemini-2.5-flash-native-audio-preview-09-2025, gemini-2.5-flash-native-audio-preview-12-2025, gemini-live-2.5-flash-preview, gemini-2.0-flash-live-001.
  • Image Generation: gemini-3.1-flash-image-preview (Nano Banana 2), gemini-3-pro-image-preview (Nano Banana Pro), gemini-2.5-flash-image (Nano Banana), imagen-4.0-generate-001, imagen-4.0-ultra-generate-001, imagen-4.0-fast-generate-001.
• DeepSeek:
  • Chat: DeepSeek-V3.1, deepseek-chat.
  • Reasoning: deepseek-reasoner.
  • Text Streaming ✔
• ElevenLabs:
  • Text-to-Speech: eleven_v3, eleven_turbo_v2_5, eleven_flash_v2_5, eleven_flash_v2, eleven_multilingual_v3 (Alpha), eleven_multilingual_v2.
  • Transcription: scribe_v2, scribe_v2_realtime, scribe_v1.
  • Sound Effects: eleven_text_to_sound_v2.
  • Audio Streaming ✔
• Inworld AI:
  • Text-to-Speech: inworld-tts-1.5-max, inworld-tts-1.5-mini, inworld-tts-1.
  • Audio Streaming ✔
• Extended OpenAI Compatible Support:
  • Alibaba Qwen:
    • Chat: qvq-max, qvq-max-latest, qvq-max-2025-03-25, qwen-vl-max, qwen-vl-plus, qwen2.5-vl-72b-instruct, qwen2.5-vl-32b-instruct, qwen2.5-vl-7b-instruct, qwen2.5-vl-3b-instruct.
    • Multimodal Chat ✔
  • Mistral AI:
    • Chat: mistral-large-2512, mistral-medium-2508, mistral-small-2506, ministral-14b-2512, ministral-8b-2512, ministral-3b-2512, magistral-medium-2509, magistral-small-2509.
    • Text Streaming ✔
  • Groq:
    • Chat: Various Groq-optimized models.
    • Text Streaming ✔
  • OpenRouter:
    • Chat: Access to hundreds of models from multiple providers.
    • Text Streaming ✔
  • Meta Llama:
    • Chat: Various Llama versions.
    • Text Streaming ✔
  • BigModel GLM-4:
    • Chat: glm-4 and variants.
    • Text Streaming ✔
  • Local Models (Ollama):
    • Chat: gemma3:1b, nemotron-3-nano, gpt-oss, llama3.1, phi3, llama3.2.
    • Text Streaming ✔

Supported Formats

• Audio:
  • Input: mp3, wav, mp4, mpeg, mpga, m4a, webm.
  • Output: pcm.
• Voice:
  • OpenAI: alloy, ash, ballad, coral, echo, sage, shimmer, verse, marin, cedar.
  • Google: Zephyr, Puck, Charon, Kore, Fenrir, Leda, Orus, Aoede, Callirrhoe, Autonoe, Enceladus, Iapetus, Umbriel, Algieba, Despina, Erinome, Algenib, Rasalgethi, Laomedeia, Achernar, Alnilam, Schedar, Gacrux, Pulcherrima, Achird, Zubenelgenubi, Vindemiatrix, Sadachbia, Sadaltager, Sulafat.
  • ElevenLabs: 50+ Voices.
• Languages:
  • Google: Arabic, German, English, Spanish, French, Hindi, Indonesian, Italian, Japanese, Korean, Portuguese, Russian, Dutch, Polish, Thai, Turkish, Vietnamese, Romanian, Ukrainian, Bengali, Marathi, Tamil, Telugu.
  • OpenAI: Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, Galician, German, Greek, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Kannada, Kazakh, Korean, Latvian, Lithuanian, Macedonian, Malay, Marathi, Maori, Nepali, Norwegian, Persian, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swahili, Swedish, Tagalog, Tamil, Thai, Turkish, Ukrainian, Urdu, Vietnamese, and Welsh.
  • ElevenLabs: Afrikaans, Arabic, Armenian, Assamese, Azerbaijani, Belarusian, Bengali, Bosnian, Bulgarian, Catalan, Cebuano, Chichewa, Croatian, Czech, Danish, Dutch, English, Estonian, Filipino, Finnish, French, Galician, Georgian, German, Greek, Gujarati, Hausa, Hebrew, Hindi, Hungarian, Icelandic, Indonesian, Irish, Italian, Japanese, Javanese, Kannada, Kazakh, Kirghiz, Korean, Latvian, Lingala, Lithuanian, Luxembourgish, Macedonian, Malay, Malayalam, Mandarin Chinese, Marathi, Nepali, Norwegian, Pashto, Persian, Polish, Portuguese, Punjabi, Romanian, Russian, Serbian, Sindhi, Slovak, Slovenian, Somali, Spanish, Swahili, Swedish, Tamil, Telugu, Thai, Turkish, Ukrainian, Urdu, Vietnamese, Welsh.

View on Fab.com Product Documentation

Use Cases:

• Truly Dynamic NPCs: Create characters whose dialogue is generated in real-time based on player actions and world events.



A third-party project built using this plugin called 'Become Human'

• Procedural Content Generation: Instantly generate rich, coherent content at runtime, from quests and item descriptions to entire lore books.
• AI-Powered Game Masters: Use Vision and Reasoning models to create an AI director that adapts the game world in real-time.
• Interactive Voice-Driven Gameplay: Combine TTS and Transcription for real, spoken conversations with in-game characters.
• Rapid Prototyping & World-Building: Use image generation and structured JSON directly in the editor to rapidly create concept art and vast amounts of world data.

Why Choose This Plugin?

• Constantly Evolving: 🧬 We provide rapid updates to support new models and features from frontier AI companies as soon as they're released.
• Production-Ready and Tested: ⚔️ All features are regularly tested with actual API keys for different use cases and scales. The plugin has been tested for over a year with updates based on user feedback.
• Generic & Adaptable by Design: 🌵 The codebase is built with a clean, generic approach, allowing for rapid adaptation to future models and API changes.
• Built by Developers, for Developers: 💻 With years of professional game development experience, we guarantee a stable, well-documented, and performant implementation.
• Dedicated Support: 📧 Email our support team for any questions or custom modification requests. We are happy to assist.

Resources & Support

• Documentation
• Discord Community
• Professional Support & Custom Development: For tailored solutions, feature requests, or enterprise support, contact our team directly at: [email protected]

View on Fab.com Product Documentation