Duix-Mobile is a software development kit for deploying real-time conversational AI characters on mobile devices. It enables the creation of interactive digital humans capable of fluid voice-to-voice interactions, featuring low-latency speech recognition and synchronized lip movements.
The project distinguishes itself through the ability to integrate custom external language models and speech providers to define an avatar's intelligence and voice. It supports the generation of real-time multilingual subtitles and provides mechanisms to track the training status of newly created digital characters.
The system covers a broad range of capabilities, including session lifecycle management, bidirectional media streaming, and audio-driven animation. It includes tools for automatic speech recognition, camera access control, and token-based session authentication. Visual rendering is handled via web-container and custom view options to decouple assets from the native host.
The SDK includes build-time optimizations for Android to prevent the obfuscation of critical system classes.