li-feishu-audio
飞书语音交互技能。支持语音消息自动识别、AI 处理、语音回复全流程。需要配置 FEISHU_APP_ID 和 FEISHU_APP_SECRET 环境变量。使用 faster-whisper 进行语音识别，Edge TTS 进行语音合成，自动转换 OPUS 格式并通过飞书发送。适用于飞书平台的语音对话场景。
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/43622283/li-feishu-qq-audioWhat This Skill Does
The li-feishu-audio skill is a powerful automation tool designed to bridge the gap between human speech and AI interaction within the Feishu (Lark) platform. It transforms Feishu into a sophisticated voice-enabled AI assistant by integrating a robust pipeline: users send voice messages in Feishu, which are automatically downloaded and converted, transcribed into text using the faster-whisper engine, processed by your AI agent, and finally synthesized back into natural-sounding voice using Microsoft's Edge TTS. The output is dynamically converted into the OPUS format, ensuring compatibility for direct playback within the Feishu mobile and desktop applications.
Installation
Installation is streamlined through the OpenClaw ecosystem. You must first ensure that the system has FFmpeg, jq, and Python 3.11+ installed. Run the command clawhub install openclaw/skills/skills/43622283/li-feishu-qq-audio to initiate the deployment. After the installation, configure your credentials by creating a .env file with FEISHU_APP_ID and FEISHU_APP_SECRET. For advanced users, you can customize the model directory and logging paths by exporting environment variables such as FAST_WHISPER_MODEL_DIR or LOG_DIR. The system automatically creates a dedicated Python virtual environment and installs the necessary dependencies, including faster-whisper and edge-tts.
Use Cases
This skill is ideal for professionals on the go who prefer voice interaction over typing. It is particularly effective for hands-free documentation, quick status updates during meetings, and rapid brainstorming sessions. In environments where typing is inconvenient, such as commuting or field work, this skill enables seamless communication with your AI agent.
Example Prompts
- "(User sends voice message): What are the action items from the team meeting notes I just sent?"
- "(User sends voice message): Draft a quick summary of the project proposal and read it back to me."
- "(User sends voice message): Help me draft an email to the client about the updated timeline."
Tips & Limitations
To optimize performance, choose a faster-whisper model size (tiny, base, or small) that balances accuracy with latency based on your hardware resources. The skill includes automated log management that clears temporary files daily to keep storage usage low. Note that edge-tts requires an active internet connection to synthesize voice, and long audio messages may experience slight delays during the conversion process from MP3 to OPUS. Always ensure your Feishu bot has the appropriate permissions for reading and writing audio messages.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-43622283-li-feishu-qq-audio": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write, file-read, external-api
Related Skills
li_itil_manager
ITIL 5 Manager - Elite IT Service Management Advisor specializing in ITSM, FinOps, and IT governance using ITIL 5 DPSM framework.
Li Etl Handle Safe
Skill by 43622283
Li Doc Answer
Skill by 43622283
Li_codeql_LLM
CodeQL 安全扫描与 LLM 智能分析融合工具。自动检测 CodeQL 安装、扫描指定目录、生成漏洞报告、LLM 分析、Jenkins 集成、输出验证 Checklist。
li_sentry_check
Multi-platform server inspection and health check skill. SSH into remote Linux servers using key-based authentication, run read-only inspection commands (CPU, memory, disk, network, services, security), and generate structured Markdown reports with anomaly highlighting. Use when the user asks to inspect servers, run health checks, check system metrics, perform 巡检/巡查, gather system status, or generate inspection reports. Compatible with nanobot, OpenClaw, and Hermes agent.