Blackwell · Nvidia · AI Agent · White House · Hugging Face
MonsterHouse is an interactive projection I shipped for Halloween
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
★ Tier-1 Source
He is built on the NVIDIA Nemotron Voice Agent with NVIDIA Nemotron ASR, Nemotron 3.5 Bolt E4B 4GB, Magpie TTS Zeroshot and Audio2Face-3D, and he runs on a single workstation.
Key facts
- To keep everything running smoothly, the reporter split the work to a pair of GPUs: the language and voice model pipeline runs on an NVIDIA RTX PRO 6000 Blackwell Max-Q, and Unreal Engine graphics
- Since each emotion requires a different 3-10 second voice sample the reporter added a “Sample your Voice” block on the UI’s tool tab
- NVIDIA Nemotron 3 Nano Omni is a VLM that gives the house visual context — He is built on the NVIDIA Nemotron Voice Agent with NVIDIA Nemotron ASR, Nemotron 3.5 Bolt E4B 4GB, Magpie TTS Zeroshot and Audio2Face-3D, and he runs on a single workstation
Summary
TL;DR: MonsterHouse is an interactive projection the reporter created for Halloween. The reporter wanted the kids visiting their house at Halloween to interact in a fun and unique way. That became MonsterHouse: a grumpy old building with pirate stories, a fiery grin and a suspicious weakness for “please.” NVIDIA Nemotron Voice Agent supplies the conversation foundation. Running it: NVIDIA Nemotron Voice Agent coordinates everything on one workstation with an NVIDIA RTX PRO 6000 Blackwell Max-Q and an NVIDIA RTX PRO 4000 Blackwell. The mouth came first.