Feishu Voice Skill for Openclaw

An automated AI agent skill that transforms text into high-quality neural speech bubbles and sends them directly to Feishu users.

shihuaijun777
v1.0.1
Apr 2, 2026
0
155
0

Install & Download

1. ClawHub CLI

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

npx clawhub@latest install feishu-voice-skill-v2

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-voice-skill-v2 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 Skill?

The Feishu Voice Skill is a specialized tool designed to bridge the gap between text-based AI processing and voice-centric communication. By utilizing the Microsoft Edge TTS engine, this skill generates realistic human-like speech from any text input. As a core component of the Openclaw Skills library, it streamlines the workflow of sending voice messages within the Feishu (Lark) ecosystem, handling everything from audio synthesis to format conversion and API delivery.

Feishu Voice Skill Use Cases

  • Automating daily stand-up reports or status updates as voice messages in Feishu.
  • Sending accessibility-friendly notifications to team members who prefer audio over text.
  • Creating localized voice alerts using various neural profiles like Xiaoxiao or Yunxi.
  • Integrating voice-based reminders into automated DevOps or project management workflows using Openclaw Skills.

How Feishu Voice Skill Works

  1. The skill captures text input and configuration parameters such as voice type and recipient ID.
  2. It interfaces with edge-tts to generate an MP3 audio file using high-fidelity neural voices.
  3. The system invokes ffmpeg to transcode the MP3 into the specific opus format required by Feishu (48kHz, 64kbps).
  4. It authenticates with the Feishu platform to retrieve a valid tenant access token.
  5. The converted audio file is uploaded to Feishu's media servers to obtain a unique file key.
  6. The skill sends a voice bubble message to the target user's Open ID.
  7. Temporary local audio files are automatically purged to maintain system hygiene.

Feishu Voice Skill Setup

To get started with this skill in the Openclaw Skills environment, ensure you have Python 3.8+ and ffmpeg installed.

# Install the necessary Python dependencies
pip install edge-tts requests

# Ensure ffmpeg is available in your system PATH

# Basic command to send a voice message
python skill.py --text "Hello, this is an automated message" --voice "zh-CN-XiaoxiaoNeural"

Feishu Voice Skill Data Schema & Taxonomy

The skill organizes its operations around the following metadata and parameter schema:

Parameter Requirement Default Description
--text Required N/A The string content to convert to speech
--voice Optional zh-CN-XiaoxiaoNeural The Microsoft Edge TTS voice model selection
--open-id Optional System Default The target recipient's Feishu Open ID
--app-id Optional System Default Your Feishu Application ID
--app-secret Optional System Default Your Feishu Application Secret

Feishu Voice Skill Advanced Features

  • Support for a wide array of neural voices including regional dialects like Liaoning and Shaanxi.
  • Seamless integration with existing Openclaw Skills automation pipelines for multi-agent workflows.
  • Automatic audio normalization and transcoding to ensure maximum compatibility with the Feishu mobile and desktop clients.
  • Stateless execution with automated cleanup of temporary MP3 and Opus artifacts.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Requires
Bins python3
Github Stars: 0
forks: 0

Featured*