The cloud-based interactive avatar virtual assistant is built using the NVIDIA Tokkio customer service AI workflow to enable interactive avatars that see, perceive, intelligently converse, and provide recommendations to enhance the customer service experience.
Serious about building interactive avatars hosted in the cloud? Want to try out the Tokkio web-based demo for yourself? Please join our Tokkio Early Access Program and share more about your use case. Please register or log in using your company email credentials to help us evaluate and grant access. Thanks for your patience as we expand this program.
Built on NVIDIA Omniverse ACE
NVIDIA Tokkio leverages Omniverse Avatar Cloud Engine (ACE), a suite of cloud-native AI models and services that make it easier to build and customize lifelike virtual assistants and digital humans. ACE is built on top of NVIDIA’s Unified Compute Framework (UCF), which provides access to the rich software tools and APIs needed to harness the wide range of skills needed for highly realistic, fully interactive avatars.
NVIDIA AI Technologies

Animation AI
Omniverse Audio2Face beta simplifies animation of a 3D character to match any voice-over track, whether you’re animating characters for a game, film, real-time digital assistants, or just for fun. You can use the app for interactive real-time applications or as a traditional facial animation authoring tool. Run the results live or bake them out, it’s up to you.
AUDIO2FACE

Conversational AI
With NVIDIA’s conversational AI solutions–including NVIDIA Riva for speech AI and NVIDIA NeMo framework for natural language processing–developers can quickly build and deploy cutting-edge applications that deliver high-accuracy and respond in far less than 300 milliseconds, the speed for real-time interactions.
Conversational AI

Vision AI
NVIDIA Metropolis enables the end-to-end computer vision (CV) workflow—from model development to deployment—for individual developers, higher education and research, and enterprises. Start with NVIDIA pre-trained models, TAO, and DeepStream to make the end-to-end computer vision AI development process easier.

Recommendation AI
NVIDIA Merlin™ is an open-source framework for building high-performing recommender systems at scale. It includes libraries, methods, and tools that streamline the building of recommenders by addressing common preprocessing, feature engineering, training, inference, and deploying to production challenges.
See NVIDIA's Tokkio and Omniverse ACE in Action

QSR Customer Service
See customers interact with Project Tokkio, an Omniverse ACE-powered conversational-AI kiosk. This reference application leverages NVIDIA Metropolis vision AI and NVIDIA Riva speech AI technology to communicate with the user. It uses NVIDIA’s NeMo Megatron-Turing 530B, a state-of-the-art language model for understanding intent, and NVIDIA Merlin to make meaningful recommendations. The 3D avatar is animated and visualized with Omniverse to deliver a visually stunning customer service experience—all in real time.

Natural, Expert Q&A Assistant
In this demo, we see one example of Project Tokkio - a “talking kiosk” reference application featuring a photorealistic, lifelike autonomous avatar responding to challenging domain-specific questions. The avatar, built in Omniverse, is a reference application that leverages several key NVIDIA technologies, including NVIDIA Riva for speech AI, NVIDIA’s NeMo Megatron Megatron-Turing 530B large language model, and a combination of NVIDIA Omniverse animation systems for facial and body animation.

DRIVE Concierge
Omniverse ACE enables DRIVE Concierge to serve as everyone’s digital assistant, helping them make recommendations, book reservations, make phone calls, and provide alerts. It’s personalized to each driver and passenger, giving every vehicle occupant their own personal concierge. Passengers can have a natural conversation with the vehicle and use voice to control many functions that previously required physical controls or touch screens.