Download
Luna AI is a virtual AI streamer framework designed to power an interactive VTuber that can go live on major platforms and chat with viewers in real time. It is built around a core assistant persona called “Luna AI,” which can be driven by a wide range of large language models and platforms, including GPT-style APIs, Claude, LangChain-based backends, ChatGLM, Kimi, Ollama, and many others. The project supports multiple rendering backends for the avatar, such as Live2D, Unreal Engine (UE), and “xuniren,” and can output to streaming platforms like Bilibili, Douyin, Kuaishou, WeChat Channels, Pinduoduo, Douyu, YouTube, Twitch, and TikTok. For voice, it integrates with numerous TTS engines (Edge-TTS, VITS-Fast, ElevenLabs, VALL-E-X, OpenVoice, GPT-SoVITS, Azure TTS, fish-speech, ChatTTS, CosyVoice, F5-TTS, MultiTTS, MeloTTS, and others), and can optionally pass the output through voice conversion systems like so-vits-svc or DDSP-SVC to change timbre.
Features
- AI-driven VTuber framework capable of streaming to platforms like Bilibili, Douyin, YouTube, Twitch, and TikTok
- Flexible LLM backend support including GPT-style APIs, Claude, LangChain stacks, ChatGLM, Kimi, Ollama, and more
- Avatar rendering via Live2D, Unreal Engine, or other supported VTuber frontends
- Integration with many TTS engines plus optional voice conversion (so-vits-svc, DDSP-SVC) for custom voice personas
- Multi-modal capabilities including Stable Diffusion image generation and visual model-based screen or image analysis
- Configurable script loops, responses, and personas for unattended AI streaming or interactive live shows
Project Samples
