OpenClaw Camera Application Tutorial

Before starting, please complete the [01-Hardware Configuration], [02-openclaw API-KEY Configuration], [03-openclaw Model Switching], [04-AI Voice Interaction Configuration], [05-Three Dialogue Solution Configuration Tests] under the Prerequisites directory. This article assumes the basic environment has been prepared and only expands on camera-related content.

1. Tutorial Objectives

This article demonstrates OpenClaw's natural language control capabilities through CSI camera peripherals. After completing this tutorial, readers can:

• Understand the basic approach to using cameras for photo capture and visual analysis with OpenClaw
• Communicate with OpenClaw through three methods: whatsapp, TUI, and voice code
• Complete four camera cases: photo archive, scene description, OCR recognition, object location and face detection
• Understand the complete chain from "user proposing visual task" to "image capture" and "result return"

2. Hardware Preparation

• OpenClaw mainboard
• CSI camera module
• Camera ribbon cable
• [Optional] Microphone module
• Wiring diagram

3. Software Preparation

If using WhatsApp, to upload images directly to WhatsApp, you need to fill in the chat_id of your newly created WhatsApp dialogue in the following path "allowFrom"

• Open your newly created WhatsApp dialogue to see the dialogue ID

• Fill this into "allowFrom":

• Terminal input the following command to take effect

openclaw gateway restart

4. Test Camera Application

Before starting this tutorial, please complete one openclaw tui basic dialogue self-check; if you haven't done it yet, see [05-Three Dialogue Solution Configuration Tests]. Additionally, please confirm the visual model has been configured. Refer to [02-openclaw API-KEY Configuration] and [03-openclaw Model Switching]. After passing, enter camera-specific testing.

Terminal input to enter TUI:

xxxxxxxxxx
openclaw tui

You can try inputting the following content in the terminal:

• Help me take a photo
• Recognize the text in this image

• Find the cup in the image (because the model will use context, remind it to retake, otherwise it might use the first photo)

• Retake a photo and organize the text into a table

5. Three Solutions for Communicating with OpenClaw

If optional AI voice module + speaker are selected, whatsapp dialogue, tui, whatsapp dialogue need to broadcast OpenClaw's reply content. You can run the following program in terminal. AI voice module dialogue does not need to run repeatedly

• Modify whether to enable broadcast parameter

xxxxxxxxxx
/home/jetson/voice_to_openclaw/.env

xxxxxxxxxx
ENABLE_TTS=true  #This parameter controls whether to broadcast. After modification and saving, run the following program in terminal

• Terminal input

xxxxxxxxxx
cd ~/voice_to_openclaw
source .venv/bin/activate
python -m src.openclaw_session_tts

5.1 whatsapp Solution

For whatsapp connection steps, please directly refer to [05-Three Dialogue Solution Configuration Tests]. This section only retains dialogue examples suitable for the camera tutorial.

After opening whatsapp, you can usually see the photos and recognition results triggered by openclaw tui earlier synchronized over.

5.2 TUI Solution

If you have completed the TUI self-check in Chapter 0, directly enter the following command in the terminal to continue the dialogue:

xxxxxxxxxx
openclaw tui

Then you can directly input camera-related commands, for example:

• Take a photo of the current scene
• Describe the scene in the camera
• Check if there are faces

You can add TUI dialogue screenshots here.

5.3 Voice Code Solution

xxxxxxxxxx
Requires optional AI voice interaction module + speaker

For voice module installation, environment configuration, and basic wake-up process, please directly refer to [04-AI Voice Interaction Configuration]. After waking up, you can directly say control content, for example:

• Help me take a photo
• Look at what's ahead
• Help me read the text in the image

You can add voice wake-up and voice control screenshots here.

6. Comprehensive Cases

Note: The following are all dialogue demonstrations using openclaw tui method. You can also choose whatsapp or voice method to complete.

6.1 Case One: Photo Archive

Experimental Objective

Let OpenClaw first complete the most basic photo capture function and save the image.

Effect Description

After execution, a photo will be generated locally, usually retaining both this photo file and latest.jpg alias for the most recent photo. This case is suitable for verifying the image capture pipeline.

Example Instructions

• Help me take a photo
• Capture the current scene
• Take a photo now for record

6.2 Case Two: Scene Description

Experimental Objective

Let OpenClaw make a brief description of the current scene after taking a photo.

Effect Description

OpenClaw can first complete photo capture, then call visual analysis script to make a one-sentence description of the image content, such as identifying desktop, people, food, or common objects.

Example Instructions

• Look at what's ahead
• Help me describe the current scene
• After taking a photo, tell me what's mainly in the camera

6.3 Case Three: OCR Table Recognition

Experimental Objective

Let OpenClaw recognize text in images and organize it into a table.

Effect Description

This case is suitable for photographing labels, cards, packaging, or simple documents, then extracting text. It can output plain text or continue to organize into tables.

Example Instructions

• Recognize the text in this image
• After taking a photo, organize the text into a table
• Find the cup in the image
• Check if there are faces
• Help me locate the phone on the right side of the desktop