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.

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.

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.