There are three technologies within ACE for Games:
• NeMo – a large language model (LLM) will help in teaching NPCs (non-player characters) to freely communicate with the player;
• Riva – automatic speech recognition and text-to-speech. Used in conjunction with NeMo;
• Omniverse Audio2Face – generation of facial animations of characters based on a single audio recording of speech.
It is not yet known how demanding ACE will be on hardware and when it will appear in real games.
