# SceneScribe, a wearable assistant for people with visual impairments

> A headset and cane prototype that answers a spoken question about what is in front of the wearer, using a camera, vision-language models and a chain of agents.

Page: https://www.whitehatdesignstudio.com/work/scenescribe/
Published by: WhiteHat Design Studio
Last updated: 7 November 2026

Prototype, assistive technology

A headset and a cane that answer a spoken question about what is in front of the wearer, built for people with visual impairments.

A hardware, B software, C AI

![A person wearing the SceneScribe headset and holding a white cane, standing in a white corridor.](https://www.whitehatdesignstudio.com/_astro/scenescribe-wearer.BU0hm0rd_SBTSs.jpg)

The headset and the cane, indoors.

## What is SceneScribe?

SceneScribe is a wearable assistant for people with visual impairments, built by WhiteHat Design Studio as a prototype. A description is only useful if it answers the question that was asked. Someone at a shelf wants to know which chocolates are there, not a paragraph about the shop. SceneScribe keeps its answers short by putting the wearer’s question first: the agents read the image through that question, and only what matters comes back.

The hardware is small: a Raspberry Pi, a camera and a microphone inside a headset shell. The cane carries its own ESP32 and connects to a Wi-Fi access point that the headset creates itself, so the two pieces find each other without any other equipment.

- **Type:** Prototype
- **Built by:** WhiteHat Design Studio
- **Sector:** Assistive technology
- **Inputs:** A hardware, B software, C AI
- **Built with:** Vision-language models, multi-agent workflow, Raspberry Pi and camera in a headset, ESP32 in the cane, speech to text and text to speech
- **Does:** Describes what the camera sees, in answer to the wearer's own question, through earphones.

## How SceneScribe works.

### Ask

The wearer holds a button and asks a question, such as which chocolates are on the shelf in front of them.

### Capture

The camera in the headset takes an image of what is in front of them.

### Read the scene

The question becomes text. An explainer agent reads the image with the question, and a wellness agent works on its reply, so the answer keeps to what was asked.

### Answer

The reply is spoken back through the connected earphones.

### Sense the way

An ESP32 in the cane joins the headset's own Wi-Fi access point and handles obstacle detection.

## On film.

Clips from the log. They have no sound, and each one says what happens.

[SceneScribe, outdoors at night. Video without sound, 28 seconds.](https://www.whitehatdesignstudio.com/media/clips/scenescribe-outdoors.mp4)

0:28, no soundA person wearing the SceneScribe headset walks along a road at night, sweeping the white cane ahead, and stops on the roadside. A 28 second excerpt of a longer recording.

## Questions about SceneScribe

### What is SceneScribe?

SceneScribe is a prototype wearable assistant for people with visual impairments, designed and built by WhiteHat Design Studio. A headset and a cane answer a spoken question about what is in front of the wearer.

### How does SceneScribe answer a question?

The wearer holds a button and asks. The headset camera takes an image, the question becomes text, a chain of language model agents reads the image through the question, and the answer is spoken through the earphones.

### Is SceneScribe a finished product?

No. SceneScribe is a prototype, and no user trial results are published. It describes what the camera sees and does not replace a guide dog or a person.

## What we do not claim

- SceneScribe is a prototype. No user trial results are published.
- It describes what the camera sees. It does not replace a guide dog or a person.

## Sources

- [TechXpert engineering portfolio, SceneScribe](https://www.techxpert.io/portfolio)

Published 5 November 2026, updated 7 November 2026.

## Read further

- [Hardware: robotics and embedded systems design](https://www.whitehatdesignstudio.com/services/hardware/)
- [Software: dashboards, web apps and automation](https://www.whitehatdesignstudio.com/services/software/)
- [AI: computer vision and edge AI](https://www.whitehatdesignstudio.com/services/ai/)
- [AI automations: aI automation for business workflows](https://www.whitehatdesignstudio.com/services/ai-automations/)
- [STM32 vs ESP32: which should your product use?](https://www.whitehatdesignstudio.com/guides/stm32-vs-esp32/)
- [What tasks can be automated with AI?](https://www.whitehatdesignstudio.com/guides/what-to-automate-with-ai/)

## Tell us what has to work.

One sentence is enough. An engineer will reply.

[Talk to an engineer](https://www.whitehatdesignstudio.com/contact/) [WhatsApp an engineer](https://wa.me/923112721007?text=Hello%20WhiteHat%20Design%20Studio%2C%20I%20would%20like%20to%20talk%20to%20an%20engineer%20about%20my%20project.)