CTBTO Vienna needed a real-time AI avatar system for their 2025 conference that could be activated without touch interaction. The system had to work in a conference environment with background noise, support multiple languages for international delegates, and replace button-based activation with natural wake-word detection.

We developed an integrated system featuring an AI avatar with real-time speech recognition and natural conversation capabilities, wake-word activation supporting 6 languages, and advanced audio processing for real-time voice interaction and response generation.