NVIDIA Omniverse ACE

NVIDIA Omniverse™ Avatar Cloud Engine (ACE) is a suite of real-time AI solutions for end-to-end development and deployment of interactive avatars and digital human applications at-scale.

Subscribe for Updates

NVIDIA Omniverse ACE powers interactive avatars like NVIDIA’s “Toy Jensen.”

The Key Benefits of ACE

Simple to Build

Enjoy realistic, advanced avatar development without the need for specialized expertise, equipment, or manually intensive workflows. With cloud-native AI microservices and AI workflows like Tokkio, Omniverse ACE enables you to build realistic avatars quickly.

Realistic Results

Bring your avatars to life using rich software tools and APIs, including Omniverse Audio2Face for simplified 3D character animation, Live Portrait for 2D image animation, Conversational AI solutions like NVIDIA Riva for natural speech- and translation-AI-based interaction, and NVIDIA NeMo for natural language processing.

Flexible Deployment

Build, configure, and deploy your avatar application across any engine in any public or private cloud. Whether you have real-time or offline requirements, Omniverse ACE enables you to develop and deploy your avatar to suit your needs.

ACE End-to-End Development Suite

ACE Components

Omniverse ACE consists of cloud APIs and customizable microservices based on NVIDIA’s UCF, full-stack AI platform, and NVIDIA RTX™ technology. These components, along with domain-specific AI workflows and low-code tooling, make up an end-to-end avatar development suite.

Subscribe for Updates

Animation AI

Bring avatars to life with realistic 2D and 3D character animation based on video or audio input.

3D animation AI uses Omniverse Audio2Face generative AI to bring to life characters in Unreal Engine and other rendering tools by creating realistic facial animation from just an audio file.
2D animation AI, called Live Portrait, enables easy animation of 2D portraits or stylized human faces using live video feeds.

Speech AI

Create deeper user engagement with avatars that can hear, understand, and speak in real-time leveraging NVIDIA Riva microservices and APIs.

Automatic Speech Recognition (ASR) dsynthesizes natural-sounding speech from raw transcripts without any additional information.
Neural Machine Translation (NMT), supports up to 34 languages including text-to-text, speech-to-text, and speech-to-speech.

Conversational AI & NLP

Develop fully autonomous, intelligent avatars using pre-trained generative AI language models.

NeMo Language service enables enterprise hyper-personalization and at-scale deployment of large language models.
Dialogue Manager is a tool for defining conversation parameters and flow to ensure a natural interaction between user and avatar.

Unified Compute Framework

Omniverse ACE is built on NVIDIA’s Unified Compute Framework (UCF),
a low-code framework for developing cloud-native, real-time, and multimodal AI applications. This enables developers to seamlessly integrate NVIDIA’s avatar technologies into their applications without the need for low-level domain and platform knowledge.

Learn More About UCF Consult the UCF Resources

AI Avatar Workflows

Developers can leverage ACE to build their own avatar solutions from the ground up, or use NVIDIA’s suite of domain-specific AI workflows for next-generation customer engagement, marketing and branding content generation, and live communications, intelligent AI-service agents, and more.

NVIDIA Tokkio

Project Tokkio is an application built with Omniverse ACE bringing AI-powered customer service to retail stores and quick-service restaurants. It comes to life using NVIDIA AI models and technology like NVIDIA Metropolis, Riva, and NeMo. Since it runs on NVIDIA’s unified computing framework (UCF), NVIDIA Tokkio can scale out from the cloud and go wherever customers need helpful avatars with responsive and natural behavior.

Learn More About NVIDIA Tokkio

NVIDIA ACE for Games

NVIDIA ACE for Games is a foundry service that transforms games through Generative AI and enables intelligent non-playable characters (NPCs) capable of natural language interactions. Developers of middleware, tools, and games can use NVIDIA ACE for Games to build and deploy customized speech, conversation, and animation AI models in their software and games through NVIDIA NeMo, Riva, and Audio2Face. NVIDIA partnered with Convai to help optimize and integrate ACE modules into NVIDIA Kairos, a demonstration showcasing how developers can leverage ACE for Games to build intelligent NPCs.

Learn More About NVIDIA ACE for Games

NVIDIA Maxine

Collaboration with global audiences can be dramatically improved when speaking in their language. NVIDIA Maxine integrates Riva’s real-time translation and text-to-speech with real-time “live portrait” photo animation and eye contact to enable better communication and understanding.

Learn More About NVIDIA Maxine