[ad_1]

At Computex 2023 in Taipei, Nvidia CEO Jensen Huang gave the world just a glimpse of what it might be like when gaming and AI collide — with a graphically stunning recreation of a cyberpunk ramen shop where you actually talk to the owner. can do.
Seriously, imagine instead of clicking on dialog options, you can hold down a button, just say something with your voice, and get an answer from a video game character. Nvidia called it “a glimpse into the future of gaming”.
Unfortunately, the actual dialog leaves a lot to be desired – maybe try GPT-4 or Sudorite next time, Nvidia?
Here’s the entire conversation I hastily transcribed:
Player: Hey Jin, how are you?
Gin: Unfortunately not so good.
how come?
I am worried about the crime here. This condition has worsened. My ramen shop got caught in the crossfire.
may i help
If you want to do something about it, I’ve heard rumors that powerful crime lord Kumon Aoki is causing all kinds of chaos in the city. That could be the root of this violence.
I’ll talk to him, where can I find him?
I heard he hangs out at the underground fight club on the east side of town. try there.
OK, I’ll go.
Be careful, Kai.
Looking at a video of a single conversation, it’s hard to see how this is any better than picking from an NPC dialogue tree – but the impressive part is that the generative AI is responding natural speech. Hopefully Nvidia will release a demo so we can try it ourselves.
/cdn.vox-cdn.com/uploads/chorus_asset/file/24689016/nvidia_ace_games_demo_crossfire.jpg)
Screenshot by Sean Hollister / The Verge
The demo was created by Nvidia and partner Convey to help promote the tools used to build it — specifically a suite of middleware called Nvidia ACE (Avatar Cloud Engine) for games that can run locally and in the cloud. Can run in both.
The full ACE suite includes the company’s Nemo tools for deploying large language models (LLM), Riva speech-to-text and text-to-speech, and other bits. it’s also incredibly cool Look The demo is, of course, made in Unreal Engine 5 with loads of ray-tracing… to the point that the chatbot part seems weak by comparison to me. At this point, we’ve seen plenty of compelling dialogue from chatbots, even if they are sometimes trite and derivative.
/cdn.vox-cdn.com/uploads/chorus_asset/file/24689017/nvidia_ace_games_demo_2.jpg)
Screenshot by Sean Hollister / The Verge
At a Computex pre-briefing, Nvidia Omniverse VP Rev Lebaredian told me that yes, the technology could scale to more than one character at a time and theoretically let NPCs talk to each other — but acknowledged that He didn’t actually see it tested.
It’s not clear that any developer will embrace the entire ACE toolkit the way the demo attempts, but hunter 2 heart of chernobyl And fort solis Nvidia will use part of “Omniverse Audio2Face,” which tries to match the animation of a 3D character’s face to their voice actor’s speech.









