OpenDuck

Turn any OpenAI-compatible model into a real-time voice chat app in 8 languages (English, Japanese, Mandarin Chinese, Spanish, French, Hindi, Italian and Portuguese) with real-time subtitles and translations.

Demo (In App)

https://github.com/user-attachments/assets/052aa02c-7be8-411e-9bb1-8f5a13515c47

Demo (Screen-aware assistance)

https://github.com/user-attachments/assets/4603ce80-9b74-4b0e-8f8c-ff242f7bdc37

Screenshots

Features

• Real-Time Voice Interaction: Chat with AI hands-free. Interrupt anytime you want like in a real conversation.
• Screen-Aware Vision: Capture screen regions or the full screen with shortcuts and let the AI see what you see.
• Live Transcription & Subtitle: Real-Time showing trascribtion and subtitle so you don't miss anything important.
• Conversation Management: Search, rename, resume, fork or delete any previous chat session from your local disk.
• Portability: Share your characters (Prompt, Avatar, Voice) easily with .openduck files.
• Live2D Characters: Attach Cubism .model3.zip models to contacts, including expression maps for emotion tags. See LIVE2D.md.
• Engineered for Efficiency: Native macOS application built with Rust and Svelte, optimizing memory for AI models.
• Low Latency: Sub-second latency from the moment you stop talking to when the AI begins speaking.
• Flexible Model Support: Built-in MLX-optimized models or connect to Ollama, LM Studio, and OpenAI-compatible endpoints.
• Multiple Languages Support: Support real-time voice chat in 8 different languages (English, Japanese, Mandarin Chinese, Spanish, French, Hindi, Italian and Portuguese) from Kokoro and Whisper Large V3

Live2D Sample Characters

The bundled Live2D demo characters, Haru and Jin Natori, use sample data from Live2D Sample Data. They are included for demonstration purposes only. Review Live2D's license and terms before using those assets outside local testing or demos.

Requirements

• Apple Silicon (M1 or later)

Installation

From Releases

1. Go to Releases
2. Download the latest openduck-beta-xxx.dmg and move it to your Applications folder
3. Start OpenDuck from your Applications folder

Technologies Used

• Tauri - Framework for building tiny, blazing fast binaries for all major desktop platforms
• Svelte - Cybernetically enhanced web apps
• Rust - A language empowering everyone to build reliable and efficient software
• MLX - Array framework for machine learning on Apple silicon

Development

Setup

git clone https://github.com/anslwy/openduck.git
cd openduck
./install.sh

Running the App

./start.sh

License

This project is licensed under the MIT License - see the LICENSE file for details.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.