OpenClaw Cruzr Platform

Full reception interface with voice conversation, employee directory, navigation, knowledge Q&A, and mood detection.

Manage employees, knowledge base, POIs, site settings, notifications. View session analytics and transcripts.

Full-featured voice agent with OpenClaw tool execution, voice cloning, and real-time transcription.

Fully local voice pipeline: FunASR + LLM (Gemini/Ollama) + GPT-SoVITS TTS. No OpenAI dependency.

Voice agent with camera-based mood detection via MediaPipe Face Mesh. Real-time facial expression analysis.

Hand-tracking gesture game using camera. Demonstrates vision-based human-robot interaction.

AI avatar with animated expressions. Visual feedback during voice conversations.

Voice call with real-time lip-synced avatar using MuseTalk.

Conversational AI with human-like video avatar. MuseTalk-powered lip synchronization.

System health status: backend, voice stack (ASR/TTS/LLM), OpenClaw connection, GPU status.

Voice synthesis engine status: GPT-SoVITS, CosyVoice, Chatterbox, OpenAI TTS availability.