← Back to Skills Marketplace
147
Downloads
1
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install minimax-feishu-voice
Description
Send native Feishu voice bubble messages via MiniMax TTS, converting text to 16kHz opus audio and delivering as a playable Feishu audio bubble.
Usage Guidance
This skill appears to do what it says: call MiniMax TTS, transcode to Feishu's required 16kHz opus format, upload, and send a native Feishu voice bubble. Before installing or using it: (1) Inspect the included script yourself (or have someone you trust do so). (2) Be aware it will read ~/.openclaw/openclaw.json for Feishu appId/appSecret and the voice_config.json file (containing your MiniMax API key) — those files contain sensitive credentials. The registry metadata did not declare required config paths, so double-check those files and store keys minimally (use least-privilege Feishu app credentials). (3) Ensure ffmpeg with libopus is installed and run the skill in a controlled environment if you do not trust the source (no homepage / unknown source). (4) If you decide to use it, consider creating Feishu credentials scoped only for sending messages and rotate keys if you remove the skill. If anything about the source or content of the script looks unfamiliar, do not provide your real credentials until you confirm.
Capability Analysis
Type: OpenClaw Skill
Name: minimax-feishu-voice
Version: 1.0.3
The skill is a legitimate integration for sending native Feishu voice messages using the MiniMax TTS API. It correctly handles audio conversion using ffmpeg via safe subprocess calls and manages credentials by reading from the expected OpenClaw and skill-specific configuration files (openclaw.json and voice_config.json). No evidence of data exfiltration, malicious execution, or prompt injection was found.
Capability Tags
Capability Assessment
Purpose & Capability
The skill name/description say it will call MiniMax TTS, convert audio to 16kHz opus, and deliver a Feishu native voice bubble; the included Python script performs exactly those steps and calls only the expected external endpoints (MiniMax API and Feishu open-apis). The use of ffmpeg to transcode is consistent with the stated purpose.
Instruction Scope
SKILL.md and the script read local config files (~/.openclaw/workspace/skills/minimax-feishu-voice/voice_config.json and ~/.openclaw/openclaw.json) to obtain the MiniMax api_key and Feishu appId/appSecret. That behavior is necessary for operation but was not reflected in the registry's 'required config paths' metadata; users should be aware the skill will read those local files containing secrets.
Install Mechanism
No install spec is provided (instruction-only + bundled script). Nothing is downloaded from external or untrusted URLs during install. The runtime will invoke ffmpeg (expected); the skill does write temporary files during processing but cleans them up.
Credentials
The script requires a MiniMax API key and Feishu appId/appSecret — these are appropriate and proportionate to the stated functionality. However, the skill metadata does not advertise these required config files/credentials, which can be surprising to users. No unrelated credentials or environment variables are requested.
Persistence & Privilege
The skill is not marked always:true, does not modify other skills, and does not request elevated system privileges. It operates on local config files and makes network calls to the documented APIs only.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install minimax-feishu-voice - After installation, invoke the skill by name or use
/minimax-feishu-voice - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
- Updated the recommended voice ID table in the documentation: removed non-working/non-existent IDs for improved accuracy.
- No changes to code or skill functionality.
v1.0.2
从voice_config.json读取api_key，不再依赖openclaw.json；更新SKILL.md文档；默认值改为female-yujie-jingpin
v1.0.1
- Updated voice configuration path to ~/.openclaw/workspace/skills/minimax-feishu-voice/voice_config.json in documentation.
- No changes to code logic; documentation improvement only.
v1.0.0
Initial release: Send native Feishu voice bubble messages using MiniMax TTS.
- Generates Feishu-compatible voice message bubbles (not MP3 attachments) from text.
- Supports customizable voice, speed, volume, and pitch via `voice_config.json`.
- Directly sends messages to Feishu users via their `open_id`.
- Requires MiniMax TTS and Feishu channel integration, plus ffmpeg installed.
- Includes sample usage commands and recommended voice options for Chinese text.
Metadata
Frequently Asked Questions
What is Minimax Feishu Voice?
Send native Feishu voice bubble messages via MiniMax TTS, converting text to 16kHz opus audio and delivering as a playable Feishu audio bubble. It is an AI Agent Skill for Claude Code / OpenClaw, with 147 downloads so far.
How do I install Minimax Feishu Voice?
Run "/install minimax-feishu-voice" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Minimax Feishu Voice free?
Yes, Minimax Feishu Voice is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Minimax Feishu Voice support?
Minimax Feishu Voice is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Minimax Feishu Voice?
It is built and maintained by xRay (@raydoomed); the current version is v1.0.3.
More Skills