Minimax Tts Cn

使用 MiniMax API 将文字转换为 MP3 语音文件。触发词：文字转语音、TTS、生成语音、生成音频、把文字转成语音、文字转MP3、生成MP3。触发后按交互流程引导用户完成 Token 配置、文字输入、音色选择，最终生成 MP3 文件发给用户。严禁使用 say 命令或通过喇叭播放，必须生成 MP3 文件。

This skill appears to do what it says: it runs a local Python CLI that posts text to minimaxi.com's TTS endpoint, decodes the returned hex audio, saves an MP3, and expects the agent to return a MEDIA:/absolute/path line so the platform sends the file. Before installing consider: (1) you will be asked to paste your MiniMax API token — it will be stored in server/.env inside the skill folder and shared by agents on the same instance, so only use a token you trust to be stored locally; (2) the only network endpoint is https://api.minimaxi.com — verify you trust that provider; (3) SKILL.md has a small documentation inconsistency about using the 'message' tool vs. MEDIA: lines — prefer following the CLI + MEDIA: workflow described in '第四步'; (4) inspect the skill folder if you need to revoke the token later (delete server/.env). If those points are acceptable, the skill is coherent with its stated purpose.

Type: OpenClaw Skill Name: minimax-tts-zh Version: 1.2.1 The skill provides a legitimate Text-to-Speech (TTS) interface for the MiniMax API. The Python script (`server/index.py`) uses standard libraries to handle API requests and manage a local configuration file for the API token. The instructions in `SKILL.md` and `README.md` are designed to guide the AI agent through a structured user interaction flow and ensure it uses the provided tool rather than local system commands (like `say`). No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.