Realtime Multimodal AI Avatar Platform
A conversational AI avatar you can talk to by text, voice or live video, with answers grounded in a structured personal knowledge base.
What I did
- Built a production-ready multimodal conversational AI avatar with Tavus Conversational Video Interface (CVI) and LLM-based persona grounding, enabling real-time text, voice and live video interactions.
- Developed a React + TypeScript frontend with live avatar streaming and a transcript UI.
- Engineered a secure Node.js backend for conversation orchestration and REST API integration.
- Implemented personalized knowledge grounding from structured Markdown for context-aware responses.
- Designed scalable, low-latency real-time session management.
Tech stack
PythonReactTypeScriptNode.jsTavus CVILLM