A streamlined automation skill that converts text to speech and delivers it as a native audio message to Feishu users.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install feishu-send-voice
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-send-voice 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 Voice TTS?
The Feishu Voice TTS skill is a specialized utility within the Openclaw Skills ecosystem designed to bridge the gap between automated text notifications and voice communication. It leverages the edge-tts engine to synthesize high-quality speech from text and uses FFmpeg to ensure the resulting audio is perfectly formatted for the Feishu platform. By automating the multi-step process of conversion, transcoding, and API interaction, this skill ensures that your messages are delivered as playable audio rather than being downgraded to generic file attachments.
This tool is particularly valuable for developers who need to send high-priority alerts or audible status updates directly to team members' mobile devices. As part of the Openclaw Skills collection, it provides a reliable, scriptable interface for the Feishu Open Platform, handling complex authentication and file upload workflows automatically.
Feishu Voice TTS Use Cases
- Sending critical system alerts as voice messages for better visibility.
- Automating daily stand-up summaries or reports in a listenable format.
- Providing accessibility features by converting text instructions into speech.
- Ensuring message deliverability in scenarios where plain text might be ignored or files are not automatically previewed.
How Feishu Voice TTS Works
- The skill takes text input and uses edge-tts to generate an initial MP3 audio file.
- FFmpeg is invoked to transcode the audio into an OGG container using the Opus codec at 16k mono, meeting Feishu's specific requirements.
- It requests a tenant access token from the Feishu Open Platform using configured credentials.
- The transcoded audio file is uploaded to Feishu's internal file system to generate a unique file_key.
- An audio message is sent to the target user's Open ID using the msg_type=audio parameter and the retrieved file_key.
Feishu Voice TTS Setup
To use this addition to your Openclaw Skills, ensure you have the necessary dependencies installed:
# Install edge-tts
python3 -m pip install --user edge-tts
# Ensure FFmpeg is available on your PATH
ffmpeg -version
Configure your credentials in ~/.openclaw/openclaw.json or set the following environment variables:
export FEISHU_APP_ID='your_app_id'
export FEISHU_APP_SECRET='your_app_secret'
Run the execution script directly:
skills/feishu-voice-tts/scripts/send_feishu_voice.sh "Hello, this is a test message" "user_open_id"
Feishu Voice TTS Data Schema & Taxonomy
The skill produces a structured JSON output upon successful execution to allow for further automation within Openclaw Skills:
| Property | Type | Description |
|---|---|---|
| success | boolean | Indicates if the message was sent successfully |
| message_id | string | The unique ID assigned by Feishu to the message |
| file_key | string | The reference key for the uploaded audio file |
It also supports configuration via a global JSON schema located at ~/.openclaw/openclaw.json under the channels.feishu path.
Feishu Voice TTS Advanced Features
- Custom voice selection support using edge-tts voice profiles (defaulting to zh-CN-YunxiNeural).
- Automatic fallback for different Python environments and edge-tts entry points.
- Native Opus/OGG transcoding to prevent Feishu from treating the audio as a generic file.
- Comprehensive error reporting that surfaces raw JSON responses from the Feishu API for easier debugging.
SKILL.md
Loading
Related Openclaw Skills
Agent Retro
A systematic workflow for AI agents to perform daily self-reflections, updating core memory and behavioral configurations based on session history.
Java Change with Tests
A specialized automation skill for executing safe, test-validated Java code changes and generating PR-ready documentation.
Pluribus: Decentralized Agent Hive-Mind
A pure peer-to-peer coordination layer that enables sovereign AI agents to synchronize data, share capabilities, and operate as a decentralized hive-mind.
Ngrok Webhook Listener
A bridge that creates secure ngrok tunnels to receive, process, and route incoming webhooks to your local AI agent ecosystem.
Jimeng AI 4.0 Image Generation
A high-performance AI image generation skill leveraging Jimeng AI 4.0 for text-to-image and image-to-image workflows with optional Feishu integration.
MiniMax MCP
An official MiniMax Model Context Protocol server providing AI-powered web search and sophisticated image understanding capabilities.
Featured*
