Generate and send high-quality Chinese AI voice messages across Feishu, Telegram, and Discord using Microsoft edge-tts.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install ms-voice-tts
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 ms-voice-tts 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 TTS?
Voice TTS is a sophisticated extension for AI agents that utilizes the Microsoft edge-tts engine to synthesize natural-sounding Chinese speech. As a key component within the Openclaw Skills ecosystem, it allows developers to transform text into high-fidelity audio files (.opus) that can be sent as native voice messages. This tool is designed to provide a more human-like interaction for automated agents, offering a wide range of neural voices including various genders and regional dialects.
The skill is particularly effective for developers who need to bridge the gap between AI text generation and multi-channel communication. By integrating this skill, agents can communicate more effectively on platforms where voice interaction is preferred, all while maintaining control over speech characteristics such as rate, pitch, and volume without the need for paid cloud API services.
Voice TTS Use Cases
- Sending automated meeting reminders and urgent notifications as voice notes on Feishu.
- Providing interactive customer support through natural AI speech in Telegram bots.
- Broadcasting system status updates or community announcements in Discord channels.
- Creating localized user experiences using regional dialects like Northeastern or Taiwanese Mandarin.
- Enhancing accessibility by providing audio versions of long text-based reports.
How Voice TTS Works
- The AI agent triggers the tts.sh script with the desired text content and optional voice parameters.
- The script calls the edge-tts engine to process the text into a high-quality .opus audio file.
- The generated audio is stored in a local directory (typically ~/.openclaw/media/) with a timestamped filename.
- The agent retrieves the file path and uses the message tool with the asVoice parameter set to true.
- The file is transmitted to the target communication channel (Feishu, Telegram, or Discord) as a native voice message.
Voice TTS Setup
This skill depends on edge-tts. Follow these steps to prepare your environment for Openclaw Skills integration:
macOS (Recommended using pipx)
# Install pipx if you haven't already
brew install pipx
pipx install edge-tts
pipx ensurepath
Linux
pip install --user edge-tts
# Ensure ~/.local/bin is in your PATH
echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc && source ~/.bashrc
Windows
pip install edge-tts
Verify Installation
edge-tts --list-voices | head -5
Voice TTS Data Schema & Taxonomy
The skill manages audio assets and metadata as follows:
| Item | Specification |
|---|---|
| Output Format | High-quality .opus (Ogg/Opus) |
| Storage Location | ~/.openclaw/media/ |
| Average File Size | 5-20 KB for standard messages |
| Recommended Text Length | 50-300 characters for optimal quality |
| Metadata Handling | Files are timestamped to prevent collisions (e.g., openclaw_voice_1710556800.opus) |
Voice TTS Advanced Features
- Granular speech control: Adjust speed (--rate), pitch (--pitch), and volume (--volume) for custom delivery.
- Diverse Voice Library: Choose from multiple neural voices such as zh-CN-YunxiNeural (Male) or zh-CN-XiaoxiaoNeural (Female).
- Dialect Support: Includes specialized voices for Northeastern (Xiaobei) and Taiwanese (HsiaoChen) accents.
- Multi-Platform Routing: Seamlessly switch between Feishu, Telegram, and Discord using a unified data structure.
- Long-Text Optimization: Strategies for segmenting text over 500 characters to maintain synthesis stability.
SKILL.md
Loading
Related Openclaw Skills
Cleanup Reporter
A local file system scanner that generates detailed reports on large directories and duplicate files to help you reclaim disk space.
Abfallkalender RV
A technical tool for AI agents to retrieve and process waste disposal schedules for the Ravensburg district via official web sources.
Data Source Verification
A systematic workflow for verifying numerical data against original research papers to maintain 100% traceable provenance.
MBTI Fortune Teller
An innovative divination tool that uses MBTI cognitive function stacks to provide structured, personality-driven answers to any question.
Prompt Engineer
A comprehensive technical framework for designing, optimizing, and securing high-performance LLM prompts and agentic workflows.
Paper Review Generator
An automated workflow for generating comprehensive Chinese research reports from academic PDF documents using OCR and large language models.
Featured*
