NVIDIA ACE for Games (original) (raw)
NVIDIA ACE is a suite of AI technologies designed to help middleware and game developers build knowledgeable, actionable, and conversational in-game characters. ACE provides ready-to-integrate cloud and on-device AI models for speech, intelligence, and animation.
Key Benefits
Small Models for Gaming
ACE offers small AI models—from speech to vision— built to enhance game characters
Optimized for On-Device Inference
AI models fine-tuned and optimized for gaming hardware, provide high accuracy and low latency within a small memory footprint.
Inference Alongside Graphics
NVIDIA In-Game Inferencing (NVIGI) plugins schedule AI inference for different models and inference backends across complex graphics workloads to maximize performance and the user experience.
Partner Experiences Powered by AI
NVIDIA ACE is being used by industry-leading game developers and ISVs to build autonomous game characters that inhabit living, breathing worlds and AI assistants that provide tips and guidance to gamers and creators.
Assistants
The Total War: PHARAOH AI advisor assists players in learning the game’s many systems and mechanics and is powered by a small on-device language model connected to Total War’s extensive game data.
Sidekicks
Streamlabs and Inworld AI introduce an intelligent streaming assistant that serves as a producer, technical assistant, and 3D sidekick.
Teammates
KRAFTON’s PUBG introduces Co-Player Characters (CPCs), AI-driven allies that communicate in natural language and act autonomously like human teammates.
Enemies
Wemade Next’s MIR5 introduces AI-powered bosses that continuously learn from previous player tactics to adapt and provide unique fights every run.
Citizens
KRAFTON’s inZOI features Smart Zois, AI-driven agents that plan, act, and reflect on their decisions to create unique character dynamics.
Characters
Dead Meat is a first-of-its-kind murder-mystery interrogation game where players can ask the suspect absolutely anything, in their own words.
Creating On-Device AI Agents
For Unreal Engine 5 developers and technical artists, a suite of NVIDIA ACE plugins is available to streamline the end-to-end AI NPC pipeline. They're local, RTX-optimized workflows bundled with ready-to-use models, governed by the MIT license.
SDKs for Custom Integrations
AI Models
Animation
Intelligence
Speech
NVIDIA Nemotron ASR
Fast & accurate automatic speech recognition (ASR), now with a reduced memory footprint and support for English, Chinese, Korean, French, German, Italian, and Japanese. The model is available in a 140M parameter size, while the two 600M versions offer a trade-off between accuracy and VRAM footprint. Additionally, these models are compatible with multi-vendor GPUs and CPUs.
Chatterbox TTS
Resemble AI’s family of TTS models includes a 350M open-source version featuring paralinguistic tagging and zero-shot voice cloning, as well as a 500M open-source version with multilingual support. These models deliver expressive voices with precise emotional and non-verbal control and are compatible with multi-vendor GPUs and CPUs.
Qwen3.5 Family
Open source, native multimodal, with reasoning capabilities optimized for on-device inference. Qwen3.5 is designed for complex agentic workflows with multilingual support. It's compatible with multi-vendor GPUs and CPUs.
Audio2Face-3D SDK
Use AI to convert streaming audio to facial blendshapes for real-time lip-syncing and facial animations on-device or in the cloud. The SDK contains C++ and Python source code under the MIT license.
Audio2Face-3D Training
The Audio2Face-3D training framework allows developers to create Audio2Face-3D models using their data. Source code is available in Python under the Apache license. Leverage audio files, blendshape data, animated geometry caches, geometry files, and transform files to get started with the training framework. The sample data is available through a custom license for evaluation only.
Models Archive
Access previous NVIDIA ACE for Games models.
More Resources
Ethical AI
NVIDIA believes Trustworthy AI is a shared responsibility, and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their supporting model team to ensure the model meets the requirements of the relevant industry and use case and addresses unforeseen product misuse.
For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards. Please report security vulnerabilities or NVIDIA AI Concerns here.
Ready to try NVIDIA ACE?