← Back to Skills Marketplace
1955
Downloads
1
Stars
33
Active Installs
7
Versions
Install in OpenClaw
/install feishu-voice
Description
飞书语音消息发送技能。将文本转换为语音并发送到飞书，支持 TTS 生成、格式转换、语速调整、时长读取、文件上传和消息发送。
Usage Guidance
Install only if you intend your text to be processed by the configured TTS dependency and the resulting audio to be uploaded and sent through Feishu. Use a trusted coze-tts installation, least-privilege Feishu bot credentials, and avoid sending secrets, regulated data, or sensitive business content unless that data flow is approved.
Capability Analysis
Type: OpenClaw Skill
Name: feishu-voice
Version: 1.2.0
The feishu-voice skill is a legitimate utility for converting text to speech and sending it as a voice message via the Feishu (Lark) platform. It uses standard system utilities (ffmpeg, ffprobe, jq) and interacts exclusively with official Feishu API endpoints (open.feishu.cn) using provided environment credentials. The script logic in scripts/send_voice.sh is transparent, follows the documented workflow, and includes proper cleanup of temporary files in /tmp.
Capability Assessment
Purpose & Capability
The documented purpose matches the implementation: it calls a coze-tts helper, converts audio with ffmpeg/ffprobe, uploads the opus file to Feishu, and sends an audio message.
Instruction Scope
Running the script sends the message immediately to the configured or supplied Feishu recipient; this is disclosed, but there is no dry-run or confirmation prompt.
Install Mechanism
No installer or hidden setup was found. The package declares required binaries, environment variables, and the coze-tts dependency; the script searches sibling, workspace, home, and opt paths for that dependency, so users should ensure the resolved coze-tts copy is trusted. Version metadata is inconsistent across files but not security-relevant here.
Credentials
Feishu app credentials and a Coze API key are proportionate to the stated function. The text is passed to coze-tts and the generated audio is uploaded to Feishu, which is expected for this skill but should be treated as external data handling.
Persistence & Privilege
No persistence, privilege escalation, background worker, broad local indexing, or destructive behavior was found. Temporary audio files are written under /tmp and removed after use.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install feishu-voice - After installation, invoke the skill by name or use
/feishu-voice - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.2.0
优化Token获取逻辑，修复参数错误，增加默认配置支持
v1.1.2
删除遗留脚本，修复硬编码路径，测试验证通过
v1.1.1
修复硬编码路径，添加智能路径解析，完善可选环境变量声明
v1.1.0
修复依赖声明：从 zhipu-tts 迁移到 coze-tts，更新文档，添加多应用配置说明
v2.0.0
重大更新：迁移到 Coze TTS，新增语速调整功能
v1.0.1
🔒 安全修复：移除所有硬编码密钥，改用环境变量读取。确保技能文档和脚本中不包含实际密钥。
v1.0.0
Initial release: 飞书语音消息发送技能。将文本转换为语音并发送到飞书，支持 TTS 生成、格式转换、时长读取、文件上传和消息发送
Metadata
Frequently Asked Questions
What is Feishu Voice?
飞书语音消息发送技能。将文本转换为语音并发送到飞书，支持 TTS 生成、格式转换、语速调整、时长读取、文件上传和消息发送。 It is an AI Agent Skill for Claude Code / OpenClaw, with 1955 downloads so far.
How do I install Feishu Voice?
Run "/install feishu-voice" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Feishu Voice free?
Yes, Feishu Voice is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Feishu Voice support?
Feishu Voice is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Feishu Voice?
It is built and maintained by xiaofei (@franklu0819-lang); the current version is v1.2.0.
More Skills