NVIDIA ACE
NVIDIA ACE is a suite of real-time AI solutions for end-to-end development of interactive avatars and digital human applications at-scale. Its customizable microservices offer the fastest and most versatile solution for bringing avatars to life at-scale, based on NVIDIA’s Unified Compute Services, full-stack AI platform and RTX technology. Leverage ACE to seamlessly integrate NVIDIA AI into your application, including Riva for speech and translation AI, Voice Font for transferring your voice to a digital avatar, NeMo LLM for natural language understanding, and Audio2Face, Audio2Emotion, Animation Graph, Omniverse Renderer or Live Portrait for AI powered 2D and 3D character animation. Or, further optimize for cloud scale with microservices and domain-specific AI workflows like NVIDIA Maxine, NVIDIA Tokkio, Animation Pipeline, and NVIDIA Kairos, to deliver advanced avatars across video conferencing customer service use cases and gaming.
Release Notes
Getting Started
Workflows
- Animation Pipeline
- Tokkio
- Tokkio Getting started
- Reference Applications
- CSP Setup Guides
- AWS
- Azure
- GCP
- Tokkio Customization
- Software Modules
- Video Storage Toolkit
- Vision and AI analytics
- UI Server
- UI
- Ingress
- Stream Distribution and Routing
- Menu
- Cart Manager
- Plugin Server
- UMIM Action Server
- Tokkio Troubleshooting
- Kairos
- Unreal Engine Integration
- NVIDIA ACE 2.1 Plugin
- Install the ACE Plugin
- NVIDIA Audio2Face
- Initial Editor Setup
- Audio2Face Connection Setting
- Add NVIDIA ACE Face Animation Support to MetaHumans
- Add ACE Audio Component to a Character
- Import Speech Clips
- Animating a Character from a Sound Wave Audio Clip
- Animating a Character from a Local WAV File (Optional)
- Adjusting Character Emotion (Optional)
- Adjusting Audio2Face Parameters (Optional)
- Troubleshooting
- Notes for Non-MetaHuman Characters
- Upgrading from a Previous Plugin Version
- Legacy Live Link Interface Documentation (Removal scheduled for a future release)
- Kairos Unreal Sample Project
- NVIDIA ACE 2.1 Plugin
- Unreal Engine Integration
Microservices
- Animation Graph Microservice
- Omniverse Renderer Microservice
- Audio2Face
- Overview
- Quick start
- Glossary of Terms
- Migrating from EA3
- Architecture overview
- Audio2Face Microservice
- Audio2Face Controller Microservice
- Sample application connecting to A2F Controller
- Sample application sending audio to Audio2Face Microservice
- Unreal Engine Interaction
- gRPC through A2F Controller
- gRPC directly with Audio2Face
- Kubernetes Deployment
- Container Deployment
- Sharing Audio2Face Compute Resources
- Parameter Tuning Guide
- Notes
- Changelog
- ACE Agent
- Getting Started
- Architecture
- Deployment
- Tutorials
- Building a Bot using Colang 1.0
- Building LangChain-Based Bots
- Building a Bot using NVIDIA RAG Examples
- Building a Bot using Colang 2.0 and Event Interface
- Customizing a Bot
- Deploying Multiple Bots
- Sample Bots
- Configuration Guide
- Bot Configurations Introduction
- General Configurations
- Slots Configurations
- Plugin Configurations
- Model Configurations
- Chat Engine Configurations
- Speech Configurations
- User Guide
- API Guide
- Best Practices
- Best Practices Introduction
- Planning your Bot
- Step 1: Choose your Bot’s Domain of Expertise
- Step 2: Determine the Conversation Flow and Knowledge Bases
- Step 3: Determine the Language Model
- Step 4: Determine the Dialog Modeling Language
- Step 5: Plan More Modalities
- Step 6: Determine the Frontend Channel
- Step 7: Determine the Deployment Infrastructure
- Managing Conversation Context
- Logging and Debugging Issues
- Security Considerations
- Reference
- Riva ASR
- Riva TTS
- Riva Translation
- Live Portrait Microservice
- Voice Font Microservice
- Resource Downloader
Licenses