This plugin provides seamless integration with leading AI language models (OpenAI, Claude, DeepSeek) and TTS models (OpenAI, ElevenLabs) through their official APIs directly in Unreal Engine.

Features:

  • Direct API connections to ElevenLabs, OpenAI, Anthropic Claude, DeepSeek services

  • Support for multiple response modes (complete responses and chunk-by-chunk streaming)

  • Blueprint-friendly implementation with simple node-based setup

  • Comprehensive model support across all providers (GPT, Claude, DeepSeek)

  • Specialized handling for DeepSeek Reasoner outputs with separate reasoning and chat responses

  • Configurable request parameters (temperature, max tokens, system prompts)

  • Cross-platform compatibility

  • Simple API key management

  • Error handling and response validation

  • No additional dependencies required beyond the plugin itself

该插件提供与领先的AI语言模型的无缝集成(开放式,开放式, 克劳德, 深塞克)和TTS模型(开放式,开放式, 电子实验室)通过他们的官方Api直接在虚幻引擎。

特征:

  • 直接API连接到ElevenLabs,OpenAI,Anthropic Claude,DeepSeek服务

  • 支持多种响应模式(完整响应和逐块流)

  • 通过基于节点的简单设置实现蓝图友好型

  • 跨所有提供商的全面模型支持(GPT,Claude,DeepSeek)

  • 具有独立推理和聊天响应的DeepSeek推理器输出的专门处理

  • 可配置的请求参数(温度、最大令牌、系统提示)

  • 跨平台兼容性

  • 简单的API密钥管理

  • 错误处理和响应验证

  • 除了插件本身之外,不需要额外的依赖

ℹ️ Note: The images with text-to-speech examples were created using the Runtime Audio Importer plugin. So, to follow these examples, you will need to install that plugin as well. However, you can also implement your own audio handling solution without using it. For text-to-text functionality, the Runtime Audio Importer is not required.

🤖 Seamlessly integrate cutting-edge AI chatbots into your Unreal Engine projects!

Transform your games and applications with powerful AI conversation capabilities and natural-sounding speech using the most advanced language models available today. This plugin provides direct access to OpenAI’s GPT models, Anthropic’s Claude, DeepSeek’s advanced reasoning models, plus high-quality TTS from OpenAI and ElevenLabs – all through simple Blueprint nodes!

Quick links:

✨ Key features:

  • Multiple AI Providers: Connect to OpenAI, Claude, and DeepSeek through their official APIs

  • Latest Models Supported: Access cutting-edge models including GPT-4o, Claude 3.7 Sonnet, and DeepSeek Reasoner

  • Flexible Response Handling: Choose between complete responses or real-time streaming (chunk by chunk)

  • Advanced Streaming TTS: Get audio chunks as they’re generated for OpenAI and ElevenLabs, enabling immediate playback while synthesis continues

  • 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

🔧 Supported models:

Text chat models:

OpenAI:
  • 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)

Text-to-Speech voices:

OpenAI TTS:
  • Alloy, Ash, Ballad, Coral, Echo

  • Fable, Onyx, Nova, Sage, Shimmer, Verse

ElevenLabs TTS:
  • Eleven Multilingual V2

  • Eleven Monolingual V1

  • Eleven Turbo V2

  • Eleven Turbo V2.5

  • Eleven Flash V2.5

💡 Perfect for:

  • Interactive NPCs with intelligent conversations and voices

  • In-game assistants and guides that speak naturally

  • Creative content generation and narration on-the-fly

  • Educational applications with AI tutoring and spoken instructions

  • AI-driven gameplay mechanics with voice feedback

  • Virtual companions with personality expressed through text and speech

  • Voice-overs and dialogue generated dynamically

Note: API usage requires accounts with respective services (OpenAI, Anthropic, DeepSeek, ElevenLabs) and may involve usage costs from these providers.

ℹ️ 注: 带有文本到语音示例的图像是使用 运行时音频导入器 插件。 因此,要遵循这些示例,您还需要安装该插件。 但是,您也可以在不使用它的情况下实现自己的音频处理解决方案。 对于文本到文本功能,运行时音频导入器不是必需的。

▪将尖端AI聊天机器人无缝集成到您的虚幻引擎项目中!

使用当今最先进的语言模型,通过强大的AI对话功能和听起来自然的语音转换您的游戏和应用程序。 此插件提供直接访问 OpenAI的GPT模型, 人类学的克劳德, DeepSeek的高级推理 型号,加上高品质 来自OpenAI的TTS电子实验室 -所有通过简单的蓝图节点!

快速链接:

▪主要特点:

  • 多个AI提供商:连接到 开放式,开放式, 克劳德,而 深塞克 通过他们的官方Api

  • 支持的最新型号:访问尖端模型,包括 GPT-4o, 克劳德3.7十四行诗,而 深塞克理性者

  • 灵活的响应处理:选择 完整的回应实时流媒体 (逐块)

  • 高级流式TTS:获取音频块,因为它们是为 开放式,开放式电子实验室,在合成继续时启用即时播放

  • 蓝图准备就绪:无需c++编码即可立即集成的简单节点

  • 跨平台:工程 所有平台 由虚幻引擎支持(窗户, 机器人, 元任务, Mac电脑, iOS的, Linux操作系统,以及更多)

  • 简易认证:所有服务的简单API密钥管理

▪支持的型号:

文本聊天模型:

开放式,开放式:
  • GPT-3.5涡轮

  • GPT-4o

  • GPT-4o迷你型

  • GPT-4-32k

  • GPT-4涡轮

  • O1

  • O1迷你

  • O3迷你

克劳德(人类学):
  • 克劳德3.7十四行诗

  • 克劳德3.5十四行诗

  • 克劳德3.5俳句

  • 克劳德3作品

深塞克:
  • 深塞克聊天

  • DeepSeek Reasoner(具有专用推理输出)

文本到语音的声音:

开放式TTS:
  • 合金,灰,民谣,珊瑚,回声

  • 寓言,缟玛瑙,新星,圣人,微光,诗句

ElevenLabs TTS:
  • 十一多语言V2

  • 十一单语V1

  • 十一涡轮V2

  • 十一涡轮V2.5

  • 十一闪V2.5

完美的:

  • 具有智能对话和声音的交互式Npc

  • 自然说话的游戏内助手和导游

  • 创造性的内容生成和即时叙述

  • 人工智能辅导和口语指导的教育应用

  • 人工智能驱动的游戏机制与语音反馈

  • 通过文字和语音表达个性的虚拟伴侣

  • 动态生成的配音和对话

注意:API使用需要具有相应服务(OpenAI,Anthropic,DeepSeek,ElevenLabs)的帐户,并且可能涉及这些提供商的使用成本。

声明:本站所有资源都是由站长从网络上收集而来,如若本站内容侵犯了原著者的合法权益,可联系站长删除。