Features

• Speech Recognition: Real-time transcription in Chinese/English/Japanese/Korean
  
• Conversation: Local large language model inference
  
• Text-to-Speech: 10+ languages, 100+ voices
  
• Live2D: Eye tracking, lip sync
  
• Frameless window, window area conforms to model outline

Privacy & Offline

• All AI computation runs locally
  
• No internet connection required
  
• Conversation data never uploaded to any server
  
• No API keys or third-party services needed

Customization

Supports importing Live2D models or static images.

Ready Out of the Box

Install and start using immediately. No Python environment, model downloads, or technical knowledge required.

Interface Languages

简体中文 | 繁體中文 | English | 日本語 | 한국어 | Deutsch | Français | Español | Español (Latinoamérica) | Português | Português (Brasil) | Italiano | Nederlands | Polski | Dansk | Suomi | Norsk | Svenska | Čeština | Magyar | Română | Български | Ελληνικά | Türkçe | ไทย | Tiếng Việt | Українська | Bahasa Indonesia | العربية | Русский

License Notice

This application is licensed under the Cubism SDK Expandable Application License from Live2D Inc.
The built-in sample character "Hiyori Momose" is provided by Live2D Inc. for demonstration purposes only.