← 返回 Skills 市场
324
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install minimax-tts-voice
功能描述
Use MiniMax speech-2.8-hd model for high-quality text-to-speech synthesis. Supports multiple Chinese and English voices. Install when needed.
安全使用建议
This skill appears to be a normal MiniMax TTS client implemented as a Python script. Before installing, you should: (1) ensure you will supply a MINIMAX_API_KEY (SKILL.md and the script require it — the registry metadata incorrectly omitted this), (2) verify you trust the MiniMax service and its domain (the script will send your API key and text to MINIMAX_BASE_URL or the default https://api.minimax.io), (3) be aware the included script also supports image generation (it will download images and write output files), (4) note small code issues (use of tempfile.mktemp and a brittle .rstrip() on BASE_URL) that are functional bugs rather than malicious behavior, and (5) review or run the script in a controlled environment if you want to inspect network traffic (to confirm calls go only to the expected API host). If you need higher assurance, ask the publisher for provenance (signed release or known source) or perform a network capture to confirm endpoints.
功能分析
Type: OpenClaw Skill
Name: minimax-tts-voice
Version: 1.0.0
The skill is a legitimate integration for the MiniMax API, providing text-to-speech and image generation capabilities. The script `scripts/minimax_media.py` uses standard libraries (requests, argparse) to interact with the official MiniMax endpoints and handles API keys securely via environment variables. No evidence of data exfiltration, malicious execution, or prompt injection was found.
能力评估
Purpose & Capability
Primary purpose is TTS and the script implements TTS using MiniMax (speech-2.8-hd). The repository and SKILL.md also expose an image-generation function (image-01) not emphasized in the skill description. Registry metadata listed 'Required env vars: none' but SKILL.md and the script require MINIMAX_API_KEY — this metadata omission is inconsistent.
Instruction Scope
Runtime instructions call the included Python script which only: reads MINIMAX_API_KEY and optional MINIMAX_BASE_URL, posts to the MiniMax API endpoints, downloads returned images (for image generation), decodes hex audio, and writes files to disk. The script does not read arbitrary local files or transmit unrelated environment data. Network calls go to BASE_URL and use the API key in the Authorization header (expected for an API client).
Install Mechanism
No install spec—this is instruction-only with an included script. Required binary is Python and the code depends on the 'requests' package (script prints an error and exits if requests is missing). No unusual downloads or archive extraction are present.
Credentials
The script legitimately needs MINIMAX_API_KEY (and optionally MINIMAX_BASE_URL) to call the MiniMax API. The registry metadata incorrectly states 'Required env vars: none', which is a mismatch that could lead to confusion. No other credentials or secrets are requested.
Persistence & Privilege
Skill is not always-enabled and has no special persistence requirements. It does write temporary or output files when generating audio/images (to provided paths or temp files), which is expected behavior for a media tool.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install minimax-tts-voice - 安装完成后，直接呼叫该 Skill 的名称或使用
/minimax-tts-voice触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release: MiniMax speech-2.8-hd TTS
元数据
常见问题
minimax-tts 是什么？
Use MiniMax speech-2.8-hd model for high-quality text-to-speech synthesis. Supports multiple Chinese and English voices. Install when needed. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 324 次。
如何安装 minimax-tts？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install minimax-tts-voice」即可一键安装，无需额外配置。
minimax-tts 是免费的吗？
是的，minimax-tts 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
minimax-tts 支持哪些平台？
minimax-tts 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 minimax-tts？
由 jlin53882（@jlin53882）开发并维护，当前版本 v1.0.0。
推荐 Skills