OpenClaw Three Conversation Scheme Configuration and Testing

1. Course Overview

This course will introduce three common conversation methods in OpenClaw and provide their respective configuration and testing methods:

• WhatsApp dialogue
• Local TUI Conversation
• AI Voice Interaction Conversation

After completing this course, you will be able to choose the most suitable conversation method for your scenario and complete basic verification.

Note: Feishu bot and AI voice interaction use the default model. If you need to change the default large model, see [03.OpenClaw Model Switching].

2. Introduction to Three Conversation Schemes

2.1 WhatsApp Scheme

Suitable scenarios:

• Remote control via mobile phone
• Letting multiple people experience OpenClaw together

Features:

• No need to stay by the device all the time
• Suitable for demonstrating "remote natural language control"

2.2 TUI Scheme

Suitable scenarios:

• Local debugging
• Quick testing
• Troubleshooting model and skill invocation issues

Features:

• Most direct
• Easiest to see commands and return results

2.3 Voice Interaction Scheme

Suitable scenarios:

• Complete AI interaction experience
• Voice wake-up and voice control
• Desktop assistant-style experience

Features:

• Strongest sense of interaction

3. WhatsApp Conversation Configuration and Testing

If the AI voice module + speaker is optional, Feishu dialogue, tui, and WhatsApp dialogue need to broadcast the content of openclaw's reply. You can run the following program on the terminal. The AI voice module dialogue does not need to be run repeatedly

• Modify whether to enable broadcast parameter

/home/sunrise/voice_to_openclaw/.env

xxxxxxxxxx
ENABLE_TTS=true
TTS_ENGINE=xunfei_ws
TTS_API_URL=wss://tts-api.xfyun.cn/v2/tts
TTS_VOICE=x4_xiaoyan
TTS_SAMPLE_RATE=16000
TTS_VOLUME=50
TTS_TIMEOUT=60
XUNFEI_TTS_SPEED=50
XUNFEI_TTS_PITCH=50
XUNFEI_TTS_TEXT_ENCODING=UTF8
XUNFEI_TTS_SIGN_HOST=ws-api.xfyun.cn
WAKE_ACK_TEXT=I am here.
TTS_MAX_CHARS=200
TTS_TRUNCATE_MODE=smart
TTS_LOCK_PATH=/tmp/voice_to_openclaw_tts.lock

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

• Enter in terminal:

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

3.1 Install WhatsApp Plugin

• Input in terminal:

xxxxxxxxxx
openclaw channels login --channel whatsapp

• After execution, a QR code usually appears. (Operate according to the [2.OpenClaw and WhatsApp Plugin Application] chapter in [12.OpenClaw Deployment and Basic Use])

Note: If no QR code is generated after running, you can delete the following files and then re-run the command.

• Scan the QR code on the mobile phone to connect. "Linked after restart" appears, proving the connection is successful

• Open the newly created conversation to see the conversation ID

• Fill this into "allowFrom" in the openclaw.json file:

xxxxxxxxxx
nano /home/sunrise/.openclaw/openclaw.json

• Restart OpenClaw gateway

xxxxxxxxxx
openclaw gateway restart

3.2 Testing Method

After creation, you can directly send test messages in WhatsApp, for example:

• Describe what you see

3.3 Common Issues

• Unable to create bot after scanning: Check network first

• Created successfully but no reply: Check if OpenClaw gateway has finished restarting

   

4. TUI Conversation Configuration and Testing

4.1 Startup Method

Enter in terminal:

xxxxxxxxxx
openclaw tui

If startup is successful, it will enter the local terminal conversation interface.

4.2 Testing Method

It is recommended to input the simplest conversation content first:

• Tell me a joke
• Introduce yourself

If basic conversation is normal, then test a hardware-related instruction, for example:

• Change the RGB light to red
• Display "Hi" on the OLED
• Read current temperature and humidity

5. AI Voice Interaction Configuration and Testing

5.1 Preparation Before Startup

• Need to select AI voice interaction module + speaker

5.2 Startup Method

xxxxxxxxxx
cd /home/sunrise/voice_to_openclaw
source .venv/bin/activate
python -m src.main

5.3 Testing Method

If using serial port wake-up mode, trigger wake-up first with "Hi,yahboom".

Then you can try saying:

• Tell me a joke
• Turn on the RGB light
• Display "Welcome to OpenClaw" on the OLED

5.4 Judgment Criteria

If the voice method can complete recognition and receive OpenClaw's reply, the following items are likely normal:

• Microphone capture is normal
• ASR is normal
• OpenClaw publishing pipeline is normal
• [Optional] TTS is normal

5.5 Common Issues

• No response to wake-up: Check serial port wake-up configuration first
• Can wake up but cannot recognize: Check ASR and API-KEY
• Can recognize but not execute: Check OpenClaw gateway configuration
• Has return but no broadcast: Check TTS switch and speaker

6. Comparison of Three Schemes

7. Recommended Testing Order

It is recommended to complete the three conversation scheme tests in the following order:

1. Test openclaw tui first
2. Then test WhatsApp bot
3. Finally test AI voice interaction