# How to talk to a voice assistant about a 3D model

Source: https://0xr.space/m/how/talk-to-a-voice-assistant-about-a-3d-model  
Published 2026-10-10, updated 2026-10-20, by ZeroXR, the maker of Model Explorer (https://0xr.space/).

Open a model at 0xr.space and press Zero, the microphone on the dock. Ask out loud: what is this model, who made it, find more like this. Zero answers by voice in the language you speak, and acts on the model: it searches your device and the Gallery, opens what it finds, points at named parts, isolates or hides them, pulls the assembly apart, cuts a section, scales it and plays its animation. In a headset it can also put a note, numbered steps or a comparison in the room.

Your speech goes to Google's Gemini Live service to be understood and answered, so this part does not run on the device. In mixed reality, if the camera is already allowed, Zero can see what you are looking at. Zero is not available in every country. It cannot make a real 3D model from a description: to explain an idea it shows a few simple shapes. It knows parts by the names in the file, and the screen from what the app reports.

## Steps

1. Open 0xr.space and open a model, from Open or the Gallery.
2. Press Zero on the dock and allow the microphone when the browser asks.
3. Speak, or tap a suggestion such as What is this model? The panel shows Listening, Thinking… and Speaking.
4. On a Meta Quest, enter the room first: Zero is on the dock there too and answers beside the model.

## Questions

### Is it free?

Yes, as a preview with no sign-in and a daily allowance per device. Your own Gemini API key in Settings lifts it.

### Which languages does it speak?

It replies in the language of your last full sentence and starts in English. A word or two does not switch it.

### Where does my voice go?

To Google's Gemini Live service, which turns it into the answer. Files you open are not sent; Zero is told the model's name and its part names. See the privacy page at https://0xr.space/privacy/ for what the camera features send and keep.

### Can it make a model I describe?

No. It can show a rough idea from simple shapes, but not build a 3D model to keep.

## Related guides

- [How to ask an AI to explain the parts of a 3D model in VR](https://0xr.space/m/how/ask-ai-to-explain-the-parts-of-a-3d-model-in-vr)
- [How the Zero free preview works, and how to add your own Gemini key](https://0xr.space/m/how/zero-assistant-free-preview-and-your-own-gemini-key)
- [How to fix microphone permission for the Zero voice assistant](https://0xr.space/m/how/fix-microphone-permission-for-the-voice-assistant)
- [How to connect the Zero assistant to an AI agent on your computer](https://0xr.space/m/how/connect-the-zero-assistant-to-an-ai-agent-on-your-computer)

