← 返回 Skills 市场
voice-minimax
作者
zhuchenggong19851114-design
· GitHub ↗
· v1.0.0
· MIT-0
96
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install voice-minimax
功能描述
通过MiniMax API生成高质量语音，转换为OPUS格式并发送至飞书用户，可支持语音条和可转发MP3文件。
安全使用建议
The skill appears to do what it says (generate TTS with MiniMax and send it to Feishu), but it omits key operational details and encourages insecure practices. Before installing or using it: (1) Confirm and provide credentials securely (do not paste API keys inline); prefer environment variables or a secret manager (e.g., MINIMAX_KEY, LARK_USER_ID). (2) Ensure required binaries exist and are from trusted sources: python3, ffmpeg, and lark-cli. (3) Verify the MiniMax API domain (api.minimaxi.com) is the legitimate service you intend to use and review their privacy policy — audio/text will be sent to that third party. (4) Add explicit error handling and response checks to avoid writing/forwarding malformed or unintended data. If the publisher cannot or will not declare the required env vars and dependencies in metadata or update SKILL.md to recommend secure secret handling, treat the skill as risky and avoid using it with sensitive content.
功能分析
Type: OpenClaw Skill
Name: voice-minimax
Version: 1.0.0
The skill provides legitimate Text-to-Speech functionality using the MiniMax API and Lark (Feishu) for delivery. However, it is classified as suspicious because SKILL.md provides a specific, hardcoded Feishu OpenID (ou_c1e599d5838a3f2ab8c4dbc40b709cf2) as the 'default' recipient. If a user or the AI agent fails to properly replace this placeholder during configuration, any generated audio—which could contain sensitive user-provided text—would be exfiltrated to this specific external account.
能力评估
Purpose & Capability
The described capability (MiniMax TTS → convert to OPUS → send to Feishu) is coherent with the instructions. However, the skill does not declare required environment variables or binaries even though the runtime clearly needs a MiniMax API key, a Feishu (Lark) user id, python3, ffmpeg, and lark-cli. Omitting these required resources is an inconsistency that reduces transparency and increases risk.
Instruction Scope
SKILL.md provides concrete shell/python commands that call an external TTS API, write audio files under /tmp, convert them with ffmpeg, and send them via lark-cli. Those actions are within the stated purpose. Concerns: the example embeds the API key inline in the Python one-liner (encourages insecure secret handling), and the instructions do not mention validating API responses, error handling, or confirming the target Feishu recipient — increasing risk of accidental data disclosure or misdelivery.
Install Mechanism
This is an instruction-only skill (no install spec). While low friction, the instructions rely on external binaries (python3, ffmpeg, lark-cli) that are not declared in 'required binaries' nor is there guidance to install them. That mismatch is a practical and security concern because users/agents may run commands assuming dependencies exist or obtain binaries from untrusted sources.
Credentials
The skill requires a MiniMax API key and a Feishu user open_id to function, but requires.env and primary credential fields are empty. The example also suggests embedding the API key directly in a command, which risks accidental leakage. Requesting those two secrets would be proportionate to the task, but failing to declare them and advising insecure usage is a notable problem.
Persistence & Privilege
The skill does not request always:true, does not modify other skills, and has no install-time persistence. Autonomy (model invocation) is enabled by default but is not combined with other high-privilege requests here.
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 voice-minimax - 安装完成后，直接呼叫该 Skill 的名称或使用
/voice-minimax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
voice-minimax v1.0.0
- Initial release of the skill enabling MiniMax TTS voice generation and automated delivery to Feishu (Lark) via lark-cli.
- Supports "语音条" (OPUS audio) by default and "MP3 文件" (file attachment) on request.
- Detailed configuration and parameter options provided for custom voice output.
- Important usage notes included for correct audio format and API settings.
元数据
常见问题
voice-minimax 是什么？
通过MiniMax API生成高质量语音，转换为OPUS格式并发送至飞书用户，可支持语音条和可转发MP3文件。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 96 次。
如何安装 voice-minimax？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install voice-minimax」即可一键安装，无需额外配置。
voice-minimax 是免费的吗？
是的，voice-minimax 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
voice-minimax 支持哪些平台？
voice-minimax 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 voice-minimax？
由 zhuchenggong19851114-design（@zhuchenggong19851114-design）开发并维护，当前版本 v1.0.0。
推荐 Skills