OpenClaw Camera Application Tutorial

Before starting, please complete [01-Peripheral Hardware Configuration], [02-OpenClaw API-KEY Configuration], [03-OpenClaw Model Switching], [04-AI Voice Interaction Configuration], and [05-Three Dialogue Configuration Tests] in the Preparation Before Use directory. This article assumes the basic environment is ready and only covers camera-related content.

1. Tutorial Objectives

This article demonstrates OpenClaw's natural language control capability through CSI camera peripherals. After completing this tutorial, readers will be able to:

• Understand the basic approach to using cameras for photo capture and visual analysis with OpenClaw
• Communicate with OpenClaw via WhatsApp, TUI, and voice commands
• Complete four camera cases: photo capture, scene description, OCR recognition, target location and face detection
• Understand the complete chain from "user raises visual task" to "image capture" and "result return"

2. Hardware Preparation

• OpenClaw main control board
• CSI camera module
• Camera cable
• [Optional] Microphone module
• Wiring diagram

3. Software Preparation

For international version:

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

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

• Fill this into "allowFrom":

• Enter the following command in the terminal to take effect

openclaw gateway restart

4. Testing Camera Application

Before starting this tutorial, please complete an openclaw tui basic conversation self-check first; if you haven't done this yet, see [05-Three Dialogue Configuration Tests]. Also, please confirm the vision model is already configured. Refer to [02-OpenClaw API-KEY Configuration] and [03-OpenClaw Model Switching]. After passing, proceed with the camera-specific test.

Enter TUI by typing the following in the terminal:

xxxxxxxxxx
openclaw tui

You can try the following in the terminal:

• Take a photo for me
• Recognize the text in this image

• Retake the shot—look for the cup in the frame. (because the model will relate to context, remind it to take a new photo, otherwise it may use the first photo)

• Take a new photo and organize the text in it into a table

5. Three Ways to Communicate with OpenClaw

If you have the optional AI voice module + speaker, the TUI and WhatsApp conversations need to broadcast OpenClaw's replies. You can run the following program in the terminal. This is not needed for AI voice module conversations.

• Modify the TTS enable parameter

xxxxxxxxxx
/home/pi/voice_to_openclaw/.env

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

• Terminal input

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

5.1 WhatsApp Solution

For WhatsApp integration steps, please refer directly to [05-Three Dialogue Configuration Tests]. This section only includes dialogue examples suitable for the camera tutorial.

You can converse directly, for example:

• Look at what's in front
• Recognize the text in the image

5.2 TUI Solution

If you have already completed the TUI self-check from chapter 0, simply type the following command in the terminal to continue the conversation:

xxxxxxxxxx
openclaw tui

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

• Take a photo of the current view
• Describe the scene in the lens
• Check if there are any faces

Here you can add TUI conversation screenshots yourself.

5.3 Voice Code Solution

xxxxxxxxxx
Requires optional AI voice interaction module + speaker

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

• Take a photo for me

• Look at what's in front

• Help me read the text in the picture

  

Here you can add voice wake-up and voice control screenshots yourself.

6. Comprehensive Cases

Note: All demonstrations below use the openclaw tui method for conversation. You can also choose WhatsApp or voice to complete.

6.1 Case 1: Photo Storage

Experiment Objective

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

Effect Description

After execution, a photo will be generated locally. Usually, both the current photo file and latest.jpg (the most recent photo alias) are kept. This case is suitable for verifying the image capture chain.

Example Commands

• Take a photo for me
• Capture the current view
• Take a photo for record now

6.2 Case 2: Scene Description

Experiment Objective

Have OpenClaw give a brief description of the current view after taking a photo.

Effect Description

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

Example Commands

• Look at what's in front
• Help me describe the current view
• Take a photo and tell me what's mainly in the lens

6.3 Case 3: OCR Table Recognition

Experiment Objective

Have OpenClaw recognize text in an image and organize it into a table.

Effect Description

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

Example Commands

• Recognize the text in this image
• Take a photo and organize the text into a table

6.4 Case 4: Target Location and Face Detection

Experiment Objective

Have OpenClaw locate a specific target in an image or detect if there are faces in the view. If a face is detected, the annotated photo will be saved by default at:

xxxxxxxxxx
/home/pi/.openclaw/media/csi-camera/annotated/latest-face.png

Effect Description

This type of task is not just "seeing" but further finding the position of the target object in the image or recognizing faces and outputting annotated results. It is suitable for interactive demonstrations and simple visual tasks.

Example Commands

• Find the cup in the picture
• Check if there are any faces
• Help me locate the phone on the right side of the desk