Open-LLM-VTuber

View on GitHub

Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D avatar running locally across platforms

★ 14K1,656 forksPython—Open-LLM-VTuber

Cross-platform voice-interactive AI companion with a Live2D avatar and desktop pet mode. Runs locally with pluggable LLM (Ollama, OpenAI, Claude, Gemini...), ASR and TTS backends, supporting voice interruption, visual perception and MCP tool servers.

Use Cases

Hands-free real-time voice chat with an LLMLocal offline AI companion with a Live2D avatarDesktop pet assistant with transparent background modeVTuber / streaming bot (includes Bilibili live script)AI character customization via YAML personas and promptsTTS translation (speak one language, output another voice)Visual perception via camera, screen recording and screenshotsVoice cloning for custom character voicesPluggable LLM/ASR/TTS module swapping by configMCP tool use inside a voice conversation

Built With

Language: Python
Frameworks: FastAPI · PyTorch · ONNX Runtime · sherpa-onnx · uvicorn · MCP · Docker · pixi · uv

Open-LLM-VTuber

Use Cases

Built With

Tags