Skip to main content

Overview

Runtime AI Chatbot Integrator Documentation

Runtime AI Chatbot Integrator is a cross-platform Unreal Engine plugin that enables seamless integration of AI chatbots and text-to-speech services directly into your projects. The plugin supports multiple leading AI providers and offers flexible chat interactions with both streaming and non-streaming response modes, as well as high-quality text-to-speech conversion with streaming capabilities.

Supported Features​

Text-to-Text Chat​

Integrate AI-powered conversational capabilities with multiple leading providers.

OpenAI​

  • GPT-5
  • GPT-5 Mini
  • GPT-5 Nano
  • GPT-3.5 Turbo
  • GPT-4o
  • GPT-4o Mini
  • GPT-4-32k
  • GPT-4 Turbo
  • GPT-4-1
  • ChatGPT-4o Latest
  • O1 Pro
  • O1
  • O3
  • O3 Mini
  • O4 Mini

Claude (Anthropic)​

  • Claude 4.5 Sonnet
  • Claude 4 Sonnet
  • Claude 4.1 Opus
  • Claude 4.0 Opus
  • Claude 3.7 Sonnet
  • Claude 3.5 Haiku
  • Claude 3 Opus

DeepSeek​

  • DeepSeek Chat
  • DeepSeek Reasoner (with dedicated reasoning output)

Gemini (Google)​

  • Gemini 2.5 Pro
  • Gemini Flash Latest
  • Gemini Flash Lite Latest
  • Gemini 2.5 Flash
  • Gemini 2.5 Flash Lite
  • Gemini 2.0 Flash
  • Gemini 2.0 Flash Lite

Grok (xAI)​

  • Grok 4 Fast Reasoning
  • Grok 4 Fast Non-Reasoning
  • Grok Code Fast 1
  • Grok 4
  • Grok 3
  • Grok 3 Mini
  • Grok 2 Vision 1212
  • Grok 2 1212
  • Grok Vision Beta

Text-to-Speech (TTS)​

Convert text to natural-sounding speech using leading TTS providers, with both standard and streaming options.

OpenAI TTS​

Multiple voice options with regular and streaming support:

  • Alloy
  • Ash
  • Ballad
  • Coral
  • Echo
  • Fable
  • Onyx
  • Nova
  • Sage
  • Shimmer
  • Verse

Models:

  • TTS-1
  • TTS-1-HD
  • GPT-4o Mini TTS

ElevenLabs TTS​

Multiple models with regular and streaming support:

  • Eleven V3 (Latest model with human-like and expressive speech generation, supports 70+ languages)
  • Eleven TTV V3 (Text to Voice design model with human-like and expressive speech, supports 70+ languages)
  • Eleven Multilingual V2 (Most lifelike model with rich emotional expression)
  • Eleven Turbo V2 (High quality, low-latency model optimized for English)
  • Eleven Turbo V2.5 (High quality, low-latency model with multilingual support)
  • Eleven Flash V2 (Ultra-fast model optimized for real-time use in English)
  • Eleven Flash V2.5 (Ultra-fast model optimized for real-time use with multilingual support)
  • Eleven Monolingual V1

Google Cloud TTS​

High-quality neural voices with extensive language support:

  • Neural2 voices
  • Studio voices
  • Wavenet voices
  • Standard voices
  • Custom Voice support
  • Multiple languages and locales
  • SSML support for fine-grained control

Azure TTS​

Microsoft's cognitive speech service with extensive voice options:

  • Neural voices across multiple languages
  • Voice styles and emotions
  • Custom voice support
  • SSML markup support

Key Features​

  • Cross-platform compatibility (Windows, Mac, Android, iOS, Linux, Meta Quest, and more)
  • Support for multiple AI and TTS providers
  • Streaming and non-streaming chat responses
  • Streaming TTS for real-time audio synthesis and processing
  • Reasoning model support with separate reasoning and content outputs (DeepSeek, Grok)
  • High-quality voice synthesis with minimal latency
  • Easy integration with Unreal Engine Blueprints and C++
  • Flexible configuration options
  • Support for 70+ languages with ElevenLabs V3 models
  • Voice listing and discovery for Google Cloud and Azure TTS

Prerequisites​

To use the plugin, you'll need API access credentials from one of the supported providers:

For audio processing, you can implement your own solution or use the Runtime Audio Importer plugin, which can import audio data in various formats (MP3, WAV, FLAC, OGG VORBIS, OGG OPUS, BINK, RAW (PCM)). For more information, see here.

Additional Resources​