NEWS · MODELS · #2842
NVIDIA’s 'MonsterHouse' demo runs Nemotron Voice Agent with Bolt E4B 4GB and Magpie TTS
MonsterHouse is an interactive Halloween projection built by an NVIDIA employee that uses the Nemotron Voice Agent pipeline: nemotron-speech-streaming-en-0.6b.gguf for ASR, Nemotron 3.5 Bolt E4B 4GB as the local LLM (with a LoRA personality adapter), Magpie TTS Zeroshot for voice, Audio2Face-3D for lip animation, and Nemotron 3 Nano Omni plus YOLO/ByteTrack for costume description and tracking, all running on a single workstation.
KEY POINTS
- MonsterHouse is an interactive Halloween projection built by an NVIDIA employee that uses the Nemotron Voice Agent pipeline: nemotron-speech-streaming-en-0.6b.gguf for ASR, Nemotron 3.5 Bolt E4B 4GB as the local LLM (with a LoRA personality adapter), Magpie TTS Zeroshot for voice, Audio2Face-3D for lip animation, and Nemotron 3 Nano Omni plus YOLO/ByteTrack for costume description and tracking, all running on a single workstation.
- The demo shows a fully local, real-time multimodal agent pipeline using an open small LLM (Bolt E4B 4GB) and NVIDIA’s Nemotron components, illustrating practical on-device conversational character deployment.
WHY IT MATTERS
The demo shows a fully local, real-time multimodal agent pipeline using an open small LLM (Bolt E4B 4GB) and NVIDIA’s Nemotron components, illustrating practical on-device conversational character deployment.