zslrmhb/Omniverse-Virtual-Assisstant
Audio2Face Avatar with Riva SDK functionality
Integrates Riva Server (speech recognition and synthesis via gRPC) with NVIDIA's Audio2Face for real-time avatar animation driven by voice input and contextual responses. The pipeline chains automatic speech recognition, Wikipedia-based natural language understanding, text-to-speech synthesis, and facial animation generation into a conversational virtual assistant. Deployed across cloud infrastructure (Riva Server in Google Cloud) and local Omniverse environments, communicating via configurable gRPC endpoints.
No commits in the last 6 months.
Stars
75
Forks
17
Language
Python
License
MIT
Category
Last pushed
Jan 02, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/zslrmhb/Omniverse-Virtual-Assisstant"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
met4citizen/TalkingHead
Talking Head (3D): A JavaScript class for real-time lip-sync using full-body 3D avatars.
livekit/livekit
End-to-end realtime stack for connecting humans and AI
Henry-23/VideoChat
实时交互数字人，可自定义形象与音色，支持音色克隆，对话延迟低至3s。Real-time voice interactive digital human, customizable...
dmisol/flexatar-virtual-webcam
Personalized Virtual Webcam for WebRTC
Sgvkamalakar/Azure-Talking-Avatar
Explore the power of Azure Text-to-Speech with interactive talking avatar, Lisa 👩🏻🦱. Choose...