← 返回 Skills 市场
139
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install sag-andy27725
功能描述
ElevenLabs text-to-speech with mac-style say UX.
安全使用建议
This skill appears to do what it says: it calls the local 'sag' CLI to send text to ElevenLabs and save playable audio. Things to consider before installing: (1) the Homebrew formula is from a third-party tap (steipete/tap) — only install if you trust that source; (2) the ELEVENLABS_API_KEY will be sent to ElevenLabs when generating audio, so avoid sending highly sensitive text; (3) generated files are written to /tmp by the examples, which may be accessible to other local users/processes — consider using a secure path if necessary; (4) rotate or scope the API key if you install for a limited purpose; and (5) verify the 'sag' binary you install matches the upstream project (homepage: https://sag.sh) if supply-chain risk is a concern.
功能分析
Type: OpenClaw Skill
Name: sag-andy27725
Version: 1.0.0
The skill is a legitimate wrapper for the ElevenLabs text-to-speech service, utilizing the 'sag' CLI tool. It provides standard installation instructions via a Homebrew tap (steipete/tap/sag) and includes helpful guidance for the AI agent on using specific audio tags and handling voice-based responses. No malicious patterns, data exfiltration, or suspicious execution logic were found in SKILL.md or _meta.json.
能力评估
Purpose & Capability
Name/description (ElevenLabs TTS, mac-style say UX) align with requirements: the skill requires the 'sag' CLI and ELEVENLABS_API_KEY. These are the expected artifacts for a CLI wrapper that calls ElevenLabs.
Instruction Scope
SKILL.md instructs the agent to run the 'sag' CLI to generate audio and save to a local path (e.g., /tmp/voice-reply.mp3). It does not ask the agent to read unrelated files, harvest environment variables beyond the declared API key, or transmit data to unexpected endpoints. The instructions are scoped to TTS usage.
Install Mechanism
Install uses a Homebrew formula 'steipete/tap/sag'. Using a third-party tap is a reasonable install route for a CLI but carries slightly higher trust risk than an official repo or widely-known package; the install will create the 'sag' binary as declared.
Credentials
Only ELEVENLABS_API_KEY (primary) is required, with optional SAG_API_KEY and voice ID envs referenced. These credentials are proportional to a TTS integration. No unrelated secrets or config paths are requested.
Persistence & Privilege
The skill is not 'always' enabled and does not request persistent system privileges or modify other skills. It can be invoked autonomously (platform default), which is expected for a skill of this type.
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 sag-andy27725 - 安装完成后，直接呼叫该 Skill 的名称或使用
/sag-andy27725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 of sag skill for ElevenLabs text-to-speech with mac-style `say` user experience.
- Supports local playback and multiple voice models (expressive, stable, fast).
- Flexible input handling with audio tags, pronunciation rules, and model-specific controls.
- Requires `ELEVENLABS_API_KEY`; install via Homebrew (`steipete/tap/sag`).
- CLI supports custom voices and integrates audio responses for chat applications.
- Documentation covers quick start commands, model options, audio tagging, and usage tips for voice replies.
元数据
常见问题
Sag Andy27725 是什么？
ElevenLabs text-to-speech with mac-style say UX. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 139 次。
如何安装 Sag Andy27725？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install sag-andy27725」即可一键安装，无需额外配置。
Sag Andy27725 是免费的吗？
是的，Sag Andy27725 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Sag Andy27725 支持哪些平台？
Sag Andy27725 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 Sag Andy27725？
由 Andy27725（@andy27725）开发并维护，当前版本 v1.0.0。
推荐 Skills