OpenClaw Three Chat Modes Configuration Testing

1. Course Overview

This course will introduce three commonly used chat modes in OpenClaw, and provides configuration and testing methods for each:

• WhatsApp chat
• Local TUI chat
• AI voice interaction chat

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

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

2. Introduction to Three Chat Modes

2.1 whatsapp Mode

Suitable scenarios:

• Remote control via phone
• Let multiple people experience OpenClaw together

Features:

• No need to stay next to the device at all times
• Suitable for demonstrating "remote natural language control"

2.2 TUI Mode

Suitable scenarios:

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

Features:

• Most direct method
• Easiest way to view commands and results

2.3 Voice Interaction Mode

Suitable scenarios:

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

Features:

• Most immersive interaction experience

3. whatsapp Chat Configuration and Testing

If the AI voice module + speaker is an optional add-on, Feishu chat, TUI, and WhatsApp chat need to play back OpenClaw's replies. You can run the following program in the terminal. AI voice module chat does not need to run it again.

• Modify the broadcast parameter

/home/jetson/voice_to_openclaw/.env

​x
# Option A: Domestic Version (Bailian)
ENABLE_TTS=true
TTS_ENGINE=cosyvoice_http
TTS_API_URL=https://dashscope.aliyuncs.com/api/v1/services/audio/tts/SpeechSynthesizer
TTS_MODEL=cosyvoice-v3-flash
TTS_VOICE=longanhuan
TTS_FORMAT=wav
TTS_SAMPLE_RATE=24000
TTS_VOLUME=50
TTS_SPEECH_RATE=1.0
TTS_PITCH_RATE=1.0
TTS_TIMEOUT=60
WAKE_ACK_TEXT=I'm here.
TTS_MAX_CHARS=200
TTS_TRUNCATE_MODE=smart
​
# Option B: Overseas Version (iFlytek International)
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
# Terminal log language: zh / en
UI_LANGUAGE=zh

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

• Enter the following in the terminal

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

3.1 Install whatsapp Plugin

Enter in terminal:

xxxxxxxxxx
openclaw channels login --channel whatsapp

After execution, a QR code usually appears.

• 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/jetson/.openclaw/openclaw.json

• Restart OpenClaw gateway

xxxxxxxxxx
openclaw gateway restart

3.2 Testing Method

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

• Tell me a joke

3.3 Common Issues

• Cannot create bot after scanning QR code: Check network first

• Creation succeeds but no reply: Check if the OpenClaw gateway has restarted

   

4. TUI Chat Configuration and Testing

4.1 Startup Method

Enter in terminal:

xxxxxxxxxx
openclaw tui

If startup is successful, you will enter the local terminal chat interface.

4.2 Testing Method

It is recommended to first try the simplest chat messages:

• Tell me a joke
• Introduce yourself

If basic chat is normal, then test a hardware-related command, for example:

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

5. AI Voice Interaction Configuration and Testing

5.1 Pre-startup Preparation

• Requires optional AI voice interaction module + speaker

5.2 Startup Method

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

5.3 Testing Method

If using serial wake mode, first trigger wake 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 an OpenClaw reply, the following are most likely working correctly:

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

5.5 Common Issues

• No response after wake: Check serial wake configuration first
• Can wake but cannot recognize: Check ASR and API-KEY
• Can recognize but does not execute: Check OpenClaw gateway configuration
• Recognition works but no voice broadcast: Check TTS switch and speaker

6. Comparison of Three Modes

7. Recommended Testing Order

It is recommended to complete the three chat mode tests in the following order:

1. First test openclaw tui
2. Then test the WhatsApp bot
3. Finally test AI voice interaction