A specialized skill for converting text into native voice bubbles across various chat platforms using edge-tts and ffmpeg.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install voice-message
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install voice-message using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Voice Message?
The voice-message skill is a powerful extension for Openclaw Skills that enables developers to send text-to-speech audio as native voice bubbles rather than standard file attachments. By leveraging Microsoft edge-tts for natural-sounding speech and ffmpeg for precise audio processing, it ensures high-quality delivery across platforms like Telegram, Discord, Signal, and WhatsApp.
One of its most critical features is the specialized support for Feishu (Lark). While many tools fail by sending audio as a file download, this skill includes dedicated logic to handle Feishu's specific API requirements, ensuring messages appear as interactive voice bubbles. It also includes advanced waveform generation for Discord, meeting strict metadata requirements for voice message compliance.
Voice Message Use Cases
- Automating personalized audio notifications for team members in Feishu or Discord using Openclaw Skills.
- Sending localized voice alerts in Telegram groups based on server status or data triggers.
- Developing accessibility-focused bots that provide audio alternatives to text messages automatically.
- Streamlining international communication by converting text to voice in multiple languages including Chinese and English.
How Voice Message Works
- The user provides a text string and selects a neural voice profile.
- The skill executes a shell script to invoke edge-tts, generating an OGG/Opus audio file.
- FFmpeg and FFprobe are used to detect the audio duration and ensure the file meets platform specifications.
- For platforms like Discord, a waveform JSON is generated to satisfy API flags.
- The Openclaw Skills runner dispatches the audio to the selected channel with the appropriate 'asVoice' metadata to trigger native bubble rendering.
Voice Message Setup
First, ensure you have the required dependencies installed on your system:
pip install edge-tts
# Install ffmpeg using your package manager
sudo apt install ffmpeg # Linux
brew install ffmpeg # macOS
You can then generate a voice file manually to test the integration:
scripts/gen_voice.sh "Hello from Openclaw Skills" /tmp/voice.ogg en-US-JennyNeural
Voice Message Data Schema & Taxonomy
| Feature | Specification |
|---|---|
| TTS Engine | edge-tts (Microsoft Edge Neural Voices) |
| Audio Format | OGG/Opus |
| Feishu IDs | open_id, chat_id, user_id, union_id, email |
| Discord Meta | duration_secs, base64 waveform JSON |
| Default Voices | zh-CN-XiaoxiaoNeural, en-US-JennyNeural |
Voice Message Advanced Features
- Custom waveform generation script to support Discord's unique IS_VOICE_MESSAGE protocol.
- Dedicated Feishu/Lark upload logic that bypasses standard attachment limitations for true voice bubble rendering.
- Multi-language support with extensible voice references for international Openclaw Skills deployments.
- Support for multiple receive ID types in Feishu, allowing for flexible routing to users or specific chat groups.
SKILL.md
Loading
Related Openclaw Skills
Pixel Office
An interactive pixel-art dashboard that visualizes your AI agents as animated characters in a virtual office environment.
Model Healthcheck
A diagnostic utility that concurrently tests all configured AI models to ensure connectivity and performance across providers.
Stock Valuation Report Generator
An automated pipeline for generating professional-grade HTML and PDF stock valuation reports featuring quantitative metrics and qualitative market research.
Trash CLI
A powerful command-line interface that enables safe file deletion by moving items to the system trash instead of permanent removal.
Polymarket Monitor
Automate Polymarket tracking by monitoring prediction odds and receiving real-time alerts when specific probability thresholds are met.
TikTok Text Overlay
A versatile tool for adding authentic TikTok-style text overlays, backgrounds, and timed animations to images and videos.
Featured*
