Runtime flow of a Tokkio avatar, with our parts in green: the provider gateway and TTS service feed our LLM and TTS classes inside the ACE Controller, which exchanges audio and animation with A2F-3D and drives the Animation Graph and the Unreal Renderer; the video goes out through VST to the browser.

NVIDIA Tokkioでカスタムアバターを動かす:ランタイム統合、日本語音声、本番運用

How we took the Character Creator 5 avatar from Part 1, packaged as a Linux renderer build, onto a Tokkio 5.0 stage: the renderer’s runtime contract, a replaced LLM and TTS behind the stock ACE Controller, Japanese speech fixes, and the GPU and video failures we met. Every checkpoint names the log or measurement behind it.

NVIDIA Tokkio live avatar streaming interface

Character Creator 5とUnreal EngineでNVIDIA Tokkio用カスタムアバターを作成する

A conversational avatar starts with a reliable character asset, not with a running service. Before connecting speech and facial animation, we need a complete character, correctly reconstructed materials, and facial morph targets that the renderer can actually drive. [1] [2] This first article explains how to prepare a Character Creator 5 (CC5) avatar for an Unreal Engine-based NVIDIA Tokkio workflow. We cover character preparation, FBX export, Reallusion Auto Setup import, and asset-level validation. The endpoint is a saved Unreal avatar and a documented handoff. Part 2 covers ACE runtime integration, Tokkio configuration, packaging, deployment, and live-stream testing. Scope of this guide: Character Creator 5 (CC5) avatar preparation, clean FBX/JSON export, …

サロゲートモデルとNVIDIA Omniverse Kit-CAEを用いたデータセンターのデジタルツイン

CFD / AI SURROGATE / OMNIVERSE KIT-CAE From CFD to an interactive data-center twin The surrogate takes a GPU load setting and the ON/OFF states of four air-conditioning units, then predicts temperature and three velocity components over 3,494,065 fluid cells. Kit-CAE visualizes the predicted fields through an in-memory pipeline. This article reports the 100-case surrogate and external accuracy results for five additional interpolation cases. The contour plots and latency benchmark use the 92% heat-generation case with air-conditioning units 1, 3 and 4 ON. All latency figures identify cold or warm operation. CONTENTS 100 Fluent cases 10 heat loads × 10 AC patterns 3.49M Fluid cells One aligned mesh 5 External …

Hello Tech Blog

DTC Tech Blogへようこそ! こんにちは。Digital Twin Center(DTC)のTech Blogへようこそ! このブログは、Digital Twin Centerで取り組んでいる技術、実験、アイデアを発信する場としてスタートしました。 テクノロジーは驚くほどのスピードで進化しています。人工知能(AI)、GPUコンピューティング、デジタルツイン、シミュレーション、可視化、仮想環境といった分野は、ますます密接につながりつつあり、研究開発に新たな可能性を生み出しています。 このブログでは、さまざまな技術トピックを幅広く紹介していく予定です。 また、完成した成果だけに焦点を当てるのではなく、私たちがどのようなことを試し、どのような過程を経て研究や開発を進めてきたのかについても共有していきたいと考えています。