← 返回 Skills 市场
Smallest Ai
作者
abhishekmishragithub
· GitHub ↗
· v1.0.1
· MIT-0
235
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install smallest-ai
功能描述
Ultra-fast text-to-speech and speech-to-text via Smallest AI's Lightning v3.1 and Pulse models. Use when the user wants to generate speech, convert text to v...
安全使用建议
This package appears to be a straightforward Smallest AI TTS/STT integration and only needs your Smallest API key and curl. Before installing: (1) verify the skill's origin (source/homepage is listed as unknown here) and prefer official provider repos if available; (2) be aware that any text and audio you send will be transmitted to smallest.ai (so avoid sending sensitive secrets or private audio you don't want shared with the provider); (3) supply a least-privilege API key (not a broad organizational admin key) and monitor usage/rate limits on the provider console; and (4) if you plan to merge the PLAN.md core changes into your system, review the proposed code edits carefully since they alter core TTS provider lists and env-key resolution.
功能分析
Type: OpenClaw Skill
Name: smallest-ai
Version: 1.0.1
The smallest-ai skill bundle provides legitimate integration for text-to-speech and speech-to-text services via the Smallest AI API. The shell and Python scripts (e.g., tts.sh, stt.py) are well-structured, transparent, and perform standard API interactions with api.smallest.ai. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found; the instructions in SKILL.md are strictly functional for voice selection and script execution.
能力评估
Purpose & Capability
Name/description, scripts, and documentation all describe TTS/STT via Smallest AI and the only required credential is SMALLEST_API_KEY; required binary (curl) is appropriate for the provided curl-based scripts. No unrelated services, credentials, or binaries are requested.
Instruction Scope
SKILL.md and included scripts instruct the agent to call smallest.ai endpoints, synthesize or transcribe audio, and write local media files. The runtime instructions do not ask the agent to read unrelated system files or other environment variables; all file I/O is local (media/tmp) and aligned with the stated functionality.
Install Mechanism
There is no remote install/download step; this is an instruction+scripts skill with bundled scripts and docs. No arbitrary external archives or shortener URLs are used in install steps, lowering install-time risk.
Credentials
Only SMALLEST_API_KEY is required (declared as primaryEnv). That single credential is appropriate and expected for a third-party TTS/STT provider; no other secrets or config paths are requested.
Persistence & Privilege
The skill is not marked always:true, does not request system-wide privileges, and does not modify other skills' configs. Agent autonomous invocation remains default but is not combined with excessive privileges 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 smallest-ai - 安装完成后，直接呼叫该 Skill 的名称或使用
/smallest-ai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
v1.0.1
Fix: update default voices (sophia, robert)
v1.0.0
Initial release: TTS (Lightning v3.1) and STT (Pulse)
元数据
常见问题
Smallest Ai 是什么？
Ultra-fast text-to-speech and speech-to-text via Smallest AI's Lightning v3.1 and Pulse models. Use when the user wants to generate speech, convert text to v... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 235 次。
如何安装 Smallest Ai？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install smallest-ai」即可一键安装，无需额外配置。
Smallest Ai 是免费的吗？
是的，Smallest Ai 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Smallest Ai 支持哪些平台？
Smallest Ai 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 Smallest Ai？
由 abhishekmishragithub（@abhishekmishragithub）开发并维护，当前版本 v1.0.1。
推荐 Skills