Get the newsletter
Nvidia · Software · Filed Jul 27, 2026 · USPTO published Nov 19, 2026 · This week's release

Nvidia Files Patent for Building Talking Avatars Like a Flowchart

Nvidia has filed a patent application for building a talking avatar like a flowchart: drag boxes onto a canvas, draw arrows between them, and the avatar reacts to what visitors say, do or touch.

A computer screen where creators set retry limits and response choices for an AI assistant by dragging and connecting visual building blocks. Drawing from patent filing US 2026/0367880 A1.
A computer screen where creators set retry limits and response choices for an AI assistant by dragging and connecting visual building blocks.All 22 drawings ↓
Publication number
US 2026/0367880 A1(US20260367880A1)
Applicant
NVIDIA Corporation
Filed · Published
Jul 27, 2026 · Nov 19, 2026
Inventors
Pascal Joël Bérard, Christian Eduard Schueller, Riccardo Roveri, Severin Klingler
Status when we published
Waiting for an examiner
Document
20 claims
US classification
717/105
Parent application
Continuation of 18/309,967 (filed May 1, 2023)(18309967)

What Nvidia's avatar flowchart builder does

Imagine you run a hotel and want a talking avatar on a lobby screen that greets guests, answers questions and helps them book a room. Today, building that usually means hiring programmers, because every new question or reaction has to be written in code.

Nvidia's patent application describes a flowchart-style builder that cuts most of that out. You drag pre-made building blocks, such as "greet the visitor" or "ask a multiple-choice question," onto a canvas and draw arrows between them. Each arrow says "if this happens, go there next." The trigger can be something the visitor says, a wave in front of a camera, or a tap on a touchscreen.

When you press deploy, the whole flowchart is packaged into a program the avatar's screen can run. You design the conversation, and the software handles the code.

From the filing · CLAIM 1
… generating a graph that defines an execution flow for the plurality of multi-modal digital avatar resources, the graph including: a plurality of nodes individually corresponding to a multi-modal digital avatar resource of the plurality of multi-modal digital avatar resources, and a plurality of directional edges connecting the plurality of nodes …

Translation: Creating a flowchart of connected steps that controls how the digital avatar behaves and responds.

How boxes and arrows steer an avatar's replies

The filing describes a way to assemble a digital avatar's behavior as a graph, which is a set of boxes (called nodes) joined by one-way arrows (called directional edges). Each box is a resource: one episode of the conversation, such as greeting someone or asking a multiple-choice question.

Each arrow is a conditional transition. It fires only when a particular modal input event happens, meaning a signal from one of the avatar's senses. The filing lists three types:

  • Audio events, like a person speaking into a microphone
  • Motion events, like someone stepping in front of a camera
  • Tactile events, like a touchscreen tap

Each box has an event handler (a small listener that waits for a chosen event and decides what to do). It can play a sound, animation, graphic or text, change a stored value, or hand control to another box. Branches of the flowchart can be active, sleeping (some listeners still on) or inactive (none listening). One example in the filing counts failed attempts and sends the avatar down a different path once a limit, such as 3 tries, is reached.

When the creator hits deploy, a compiler (a program that turns a design into runnable instructions) packages the boxes and the graph into one bundle for the device to run.

From the filing · THE ABSTRACT
… a first directional edge associated with a transition of the execution flow from the first node to the second node conditioned on an event handler of the first node responding to an occurrence of the first modal input event …

Translation: Moving from one step in the flowchart to the next only after the avatar reacts to a specific user action.

What this means for businesses running avatars

If you have used a kiosk or website chat window that answers questions, this filing aims at making those easier and cheaper to build and change. The patent's own background says avatar creators usually have to team up with programmers for each new use. A visual builder with templates, such as the restaurant ordering or hotel reservation templates it mentions, could let a business adjust what an avatar says without a code change.

For Nvidia, the application describes a toolkit for people who build avatars on an avatar-building platform, and the description says the avatar's AI parts can run on GPUs, the company's core chips. It is a patent application, not a product, and nothing in it says when or whether anything will ship.

This is the 30th Nvidia filing we've tracked since May on text to 3D characters, building on earlier work like the lip sync fix and the single photo head avatar.

Source: US 2026/0367880 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time Nvidia patent news breaks.

There are more where this came from

We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.

The drawings · 22 sheets

22 drawing sheets from US 2026/0367880 A1 · click any drawing to enlarge

Turning avatar behavior settings into functional building blocks, drawing sheet 1 from US 2026/0367880 A1
Sheet 1 Turning avatar behavior settings into functional building blocks
How user triggers turn into avatar actions, drawing sheet 2 from US 2026/0367880 A1
Sheet 2 How user triggers turn into avatar actions
Passing conversation control between nested avatar steps, drawing sheet 3 from US 2026/0367880 A1
Sheet 3 Passing conversation control between nested avatar steps
Networked servers that build and run the virtual assistant, drawing sheet 4 from US 2026/0367880 A1
Sheet 4 Networked servers that build and run the virtual assistant
Drag and drop editor for assembling an avatar conversation, drawing sheet 5 from US 2026/0367880 A1
Sheet 5 Drag and drop editor for assembling an avatar conversation
Setting retry limits for an avatar when speech is misunderstood, drawing sheet 6 from US 2026/0367880 A1
Sheet 6 Setting retry limits for an avatar when speech is misunderstood
Expanding a single conversational step into smaller subtasks, drawing sheet 7 from US 2026/0367880 A1
Sheet 7 Expanding a single conversational step into smaller subtasks
Pop up questionnaire for an avatar to gather user choices, drawing sheet 8 from US 2026/0367880 A1
Sheet 8 Pop up questionnaire for an avatar to gather user choices
Show the other 14 sheets
Connecting avatar actions into a visual conversation flow, drawing sheet 9 from US 2026/0367880 A1
Sheet 9 Connecting avatar actions into a visual conversation flow
Setting up triggers and responses for one conversation step, drawing sheet 10 from US 2026/0367880 A1
Sheet 10 Setting up triggers and responses for one conversation step
Building and launching an interactive avatar from a template, drawing sheet 11 from US 2026/0367880 A1
Sheet 11 Building and launching an interactive avatar from a template
Choosing trained AI models to handle specific avatar tasks, drawing sheet 12 from US 2026/0367880 A1
Sheet 12 Choosing trained AI models to handle specific avatar tasks
Chip hardware setups that run and train avatar AI models, drawing sheet 13 from US 2026/0367880 A1
Sheet 13 Chip hardware setups that run and train avatar AI models
Server center layers coordinating computing power for avatars, drawing sheet 14 from US 2026/0367880 A1
Sheet 14 Server center layers coordinating computing power for avatars
Computer circuits running instructions that animate an avatar, drawing sheet 15 from US 2026/0367880 A1
Sheet 15 Computer circuits running instructions that animate an avatar
Mobile device sensors and chips powering an interactive assistant, drawing sheet 16 from US 2026/0367880 A1
Sheet 16 Mobile device sensors and chips powering an interactive assistant
Hardware parts that run the avatar software on a computer, drawing sheet 17 from US 2026/0367880 A1
Sheet 17 Hardware parts that run the avatar software on a computer
Inside a multi-core processor chip with built-in graphics, drawing sheet 18 from US 2026/0367880 A1
Sheet 18 Inside a multi-core processor chip with built-in graphics
Training and rolling out AI models for real-world use, drawing sheet 19 from US 2026/0367880 A1
Sheet 19 Training and rolling out AI models for real-world use
Layers of cloud software and chips that support the AI, drawing sheet 20 from US 2026/0367880 A1
Sheet 20 Layers of cloud software and chips that support the AI
Improving an existing AI model with custom customer data, drawing sheet 21 from US 2026/0367880 A1
Sheet 21 Improving an existing AI model with custom customer data
Using pre-trained models to help label training images faster, drawing sheet 22 from US 2026/0367880 A1
Sheet 22 Using pre-trained models to help label training images faster
Patent filing page

Watchlists this filing belongs to

All watchlists →
Reader comments

No comments yet

Start the discussion

Real name or a handle, either is fine. Comments are read by a person before they appear, so allow a little time. Keep it about the filing.