A powerful integration that uses Microsoft Edge's free text-to-speech engine to send professional voice messages directly to Feishu.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install feishu-edge-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 feishu-edge-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 Feishu Edge TTS?
The Feishu Edge TTS skill provides a cost-effective way to bring high-quality vocalization to your workspace. By utilizing the Microsoft Edge TTS engine, this skill allows users to convert text into natural-sounding speech without the need for expensive Azure API keys. It is a vital component for developers looking to expand their Openclaw Skills library with audio-based notifications, delivering authentic Feishu voice bars that users can tap and play instantly.
This tool supports a wide range of global languages and diverse voice profiles, from professional male and female voices to regional dialects. Whether you are building an automated news broadcaster or a personalized greeting bot, this skill ensures that your messages are delivered with clarity and personality, enhancing the overall user experience within the Feishu ecosystem.
Feishu Edge TTS Use Cases
- Automating daily team briefings or morning greetings in Feishu groups.
- Sending urgent system alerts that stand out more than standard text notifications.
- Providing multi-lingual audio support for global teams using localized AI voices.
- Creating interactive bots that respond with regional dialects to increase team engagement.
- Generating accessible versions of text-based documentation for hands-free listening.
How Feishu Edge TTS Works
- The user inputs text and selects a voice profile through the command-line interface provided by the Openclaw Skills framework.
- The skill connects to the Microsoft Edge TTS service to synthesize the text into an audio file.
- System dependencies like ffmpeg are used to format the audio for optimal compatibility.
- The skill authenticates with the Feishu API using the provided App ID and Secret.
- The generated audio is uploaded and delivered as a native voice message to a specific Chat ID.
Feishu Edge TTS Setup
To get started with this skill in your Openclaw Skills environment, follow these steps:
# Install the necessary Python library
pip install edge-tts
# Install system dependencies (Ubuntu/Debian)
sudo apt-get install -y ffmpeg
# Configure your Feishu environment variables
export FEISHU_APP_ID="cli_your_id"
export FEISHU_APP_SECRET="your_secret"
export FEISHU_CHAT_ID="oc_your_chat_id"
# Send a test voice message
bash scripts/send_voice.sh -t "Hello from Openclaw Skills" -v en-US-JennyNeural
Feishu Edge TTS Data Schema & Taxonomy
The skill organizes its operations through a combination of environment variables and local scripts to ensure efficient delivery of Openclaw Skills content.
| Component | Type | Description |
|---|---|---|
FEISHU_APP_ID |
Environment Var | The unique ID of the Feishu custom application. |
DEFAULT_VOICE |
Config Variable | The fallback AI voice used if none is specified (e.g., zh-CN-XiaoxiaoNeural). |
scripts/send_voice.sh |
Shell Script | The main entry point for processing text and sending audio. |
examples/crontab.txt |
Template | Sample configuration for scheduling automated voice messages. |
Feishu Edge TTS Advanced Features
- Support for over 100 languages and 400+ unique neural voices for global reach.
- Fine-grained audio control including adjustable speech rates (-50% to +50%) and pitch modifications.
- Batch processing mode to read multiple lines from a text file and send them as sequential voice messages.
- No-send option to generate and preview audio files locally before broadcasting to the team.
- Custom configuration files to set workspace-wide defaults for voice and tone.
SKILL.md
Loading
Related Openclaw Skills
Daily News Skill
A customizable AI news agent that automatically aggregates, summarizes, and broadcasts news via voice for a streamlined information experience.
SEC Filing Scanner for M&A
Automate the extraction and analysis of SEC EDGAR filings to streamline financial due diligence and corporate risk assessment.
Market Intelligence for M&A
A professional-grade research skill for automating competitive landscape mapping and market sizing for M&A due diligence.
M&A Deal Screening & Target Evaluation
A professional evaluation framework designed to score and qualify acquisition targets against rigorous investment criteria.
Feishu Voice Skill
Empowers AI agents to send authentic, playable voice messages directly to Feishu users instead of standard file attachments.
Task Development Workflow
A structured, quality-first development lifecycle for AI agents involving rigorous planning, test-driven development, and pull request reviews.
Featured*
