Feishu Edge TTS Voice Sender (Windows) for Openclaw

A specialized Windows skill for converting text to speech and sending it as native Feishu voice bubbles.

ztxdcyy
v1.0.0
Mar 6, 2026
0
901
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install feishu-edge-tts-win

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install feishu-edge-tts-win 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 Voice Sender (Windows)?

This skill enables developers and teams to automate voice communications within the Feishu (Lark) ecosystem on Windows environments. By leveraging Microsoft's free Edge TTS engine, it generates natural-sounding speech from text and handles the complex conversion and API upload process required to display these as interactive voice bubbles rather than static file attachments. As a powerful addition to the Openclaw Skills library, it simplifies the workflow of programmatically interacting with corporate messaging platforms using neural voice technology.

Feishu Edge TTS Voice Sender (Windows) Use Cases

  • Sending automated status updates via voice in Feishu groups.
  • Enhancing accessibility for team notifications through audio feedback.
  • Integrating with AI agents to provide verbal responses in chat interfaces.
  • Developing interactive bots that respond with high-quality, human-like voice bubbles.

How Feishu Edge TTS Voice Sender (Windows) Works

  1. The script utilizes the edge-tts library to convert user-provided text into a high-quality MP3 audio file.
  2. It calls ffmpeg to transcode the MP3 into the OPUS format, which is the specific standard required for native Feishu voice messages.
  3. The skill interacts with the Feishu API to upload the processed OPUS file and retrieve a unique file_key.
  4. A final API message request is sent with msg_type set to audio, ensuring the recipient receives a playable voice bubble in their chat UI.

Feishu Edge TTS Voice Sender (Windows) Setup

First, install the required Python dependency:

pip install edge-tts

You must also have ffmpeg installed and available in your system PATH. Verify your installation with:

ffmpeg -version

Ensure your Feishu credentials (appId and appSecret) are configured in your global Openclaw configuration file. You can then run the skill using the following command structure:

python .\send_voice.py "Your Message Text" YOUR_FEISHU_OPEN_ID --voice zh-CN-XiaoxiaoNeural --config %USERPROFILE%\.openclaw\openclaw.json

Feishu Edge TTS Voice Sender (Windows) Data Schema & Taxonomy

The skill utilizes the following metadata and configuration structure to process requests within the Openclaw Skills framework:

Parameter Source Description
appId openclaw.json Your Feishu application identification string.
appSecret openclaw.json Your Feishu application secret key.
voice CLI Argument The specific neural voice model (default: zh-CN-XiaoxiaoNeural).
open_id CLI Argument The unique identifier for the recipient or chat group.
file_key Feishu API A temporary key generated during the audio upload process.

Feishu Edge TTS Voice Sender (Windows) Advanced Features

  • Uses Microsoft Edge's advanced neural TTS for high-fidelity, free-to-use speech synthesis.
  • Automated transcoding logic ensures compatibility with the Feishu voice bubble UI.
  • Seamless integration with existing Openclaw Skills configuration files for centralized credential management.
  • Direct support for the zh-CN-XiaoxiaoNeural voice for natural Chinese language delivery.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*