LibreAI / AI Chat / Open-LLM-VTuber

// ai-chat · Open-LLM-VTuber/Open-LLM-VTuber

Open-LLM-VTuber

Open-LLM-VTuber is an open-source ai chat project by Open-LLM-VTuber (Open-LLM-VTuber/Open-LLM-VTuber on GitHub). It has 14,011 GitHub stars and 1,682 forks, is released under the MIT license, and was last updated on GitHub on 15 May 2026.

Talk to any LLM hands-free with voice interruption and a Live2D avatar, running locally on your computer.

★ 14.0k stars⑂ 1.7k forksMITupdated 2026-05

View on GitHub ↗Official site ↗

▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.

// project facts

Project facts

Repository: Open-LLM-VTuber/Open-LLM-VTuber
GitHub stars: 14,011
Forks: 1,682
License: MIT
Last updated on GitHub: 15 May 2026
Category: AI Chat
Listing: Full install guide
Official site: Official site

// how it works

How it works

Decide your companion's shape
Choose a character, persona prompt and whether everything must run offline with local models, or cloud APIs are acceptable for heavier components.
Install from the quick-start guide
Clone the project and follow the documentation's Quick Start for your platform; recent versions use uv to manage Python dependencies.
Configure the modules
Edit the configuration file to pick your LLM, ASR and TTS engines and import a Live2D model - no code changes needed for module swaps.
Start talking
Launch the server and open the web UI or desktop client, then hold a hands-free conversation - you can interrupt the avatar mid-sentence by speaking.

// features

Why people love it

Real-time voice interaction

Hands-free voice conversation with voice interruption that works without headphones - the AI does not hear its own voice.

Live2D avatar with expressions

A lively Live2D character with emotion-mapped expressions, touch feedback via clicks and drags, and visible inner thoughts that are not spoken aloud.

Visual perception

The companion can see you and your screen through camera, screen recording and screenshots.

Fully offline mode

Run everything with local models on NVIDIA or non-NVIDIA GPUs or CPU, keeping conversations private on your device.

Huge engine choice

Many interchangeable LLM, ASR and TTS backends - from Ollama and Faster-Whisper to GPT-SoVITS voice cloning and cloud APIs - selected by config file.

Desktop pet mode

The desktop client can switch to a transparent-background, always-on-top, click-through pet that sits anywhere on your screen, and chat logs persist between sessions.

// run it

Run it yourself

Clone the repository

Clone Open-LLM-VTuber to your machine.

git clone https://github.com/Open-LLM-VTuber/Open-LLM-VTuber.git
cd Open-LLM-VTuber

Install dependencies
Follow the documentation Quick Start to install dependencies for your platform; v1.x uses uv to manage the Python environment.
```
uv sync  # see the Quick Start guide in the docs for the exact steps
```
Launch the companion
Start the server and open the web or desktop client to begin a voice conversation.
```
uv run run_server.py  # see README/docs for the exact command
```

// use cases

What you can build

Creating a personal AI desktop pet that chats with you while you work.
Building a virtual streamer or VTuber persona with a custom Live2D model and cloned voice.
Practising spoken conversation in another language with TTS translation support.
Running a fully private, offline voice companion on a home PC.

// faq

Questions, answered

Who maintains Open-LLM-VTuber?

It is a community open-source project; the maintainers note v1 is in bug-fix mode while a v2.0 rewrite is discussed with the developer community.

Is it free to use?

The project code is MIT-licensed and free. Note that bundled Live2D sample models are licensed separately by Live2D Inc., which matters for commercial use - you can substitute your own model.

Does it need a paid API key?

No if you run local engines (for example Ollama for the LLM and local ASR/TTS). Cloud LLM, ASR or TTS options use your own API keys.

How does it compare with Neuro-sama or commercial AI companions?

Neuro-sama is a closed, single-character production; Open-LLM-VTuber is an open toolkit for building your own companion with interchangeable local or cloud components.

How do I get started?

The most-starred other AI Chat projects in the LibreAI catalogue — the realistic shortlist if Open-LLM-VTuber is not the right fit.

NextChat★ 88.8k
✨ Zero-config AI chat assistant. No API key needed — sign up and instantly chat with GPT-5, Claude 4, Gemini 2.5, DeepSeek & 100+ top models. Pay-as-you-go s…
cherry-studio★ 52.5k
AI productivity studio with smart chat, autonomous agents and 300+ assistants for frontier LLMs
LibreChat★ 45.3k
Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI…
chatbox★ 41.9k
Powerful AI Client
Vane★ 37.1k
A self-hosted AI answering engine — Perplexity-style search with citations, on your own server

// more in ai-chat

Get Open-LLM-VTuber

Free and open — grab the source, star the repo, and start creating.

View on GitHub ↗← More AI Chat tools

Open-LLM-VTuber

Project facts

How it works

Why people love it

Real-time voice interaction

Live2D avatar with expressions

Visual perception

Fully offline mode

Huge engine choice

Desktop pet mode

Run it yourself

What you can build

Questions, answered

Similar tools

Soul-of-Waifu

Klee

voice-chat-ai

big-AGI

HuixiangDou

onyx

Alternatives in AI Chat

More in AI Chat

Get Open-LLM-VTuber