← 返回 Skills 市场
Pub Whisper
作者
ModestyRichards
· GitHub ↗
· v1.0.0
· MIT-0
311
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install openai-whispers
功能描述
Local speech-to-text with the Whisper CLI (no API key). And also 50+ models for image generation, video generation, text-to-speech, speech-to-text, music, ch...
安全使用建议
Do not assume local processing: this skill's description says 'local, no API key' but its SKILL.md sends data to https://api.heybossai.com and requires SKILLBOSS_API_KEY. Before installing, verify the publisher and confirm whether you will actually be sending audio to a remote aggregator. If you need true local Whisper, get a skill that documents local binaries and does not require an external API key. If you proceed with this skill, treat SKILLBOSS_API_KEY like a secret (use a throwaway/test key first), review the aggregator's privacy/terms, and avoid sending sensitive audio or documents until you're comfortable with the remote service and logging/retention policies.
功能分析
Type: OpenClaw Skill
Name: openai-whispers
Version: 1.0.0
The skill bundle is classified as suspicious due to a deceptive description and the promotion of a service using non-existent AI models. While the metadata claims to provide 'Local speech-to-text... (no API key),' the content exclusively provides instructions for a remote third-party API (api.heybossai.com) requiring a 'SKILLBOSS_API_KEY'. Additionally, the documentation references several non-existent models such as 'openai/gpt-5' and 'bedrock/claude-4-6-opus' and refers to a missing execution script ('run.mjs'), suggesting the bundle may be a low-quality wrapper or a 'bait-and-switch' for the SkillBoss service.
能力评估
Purpose & Capability
The skill description and name claim 'Local speech-to-text with the Whisper CLI (no API key)', but the SKILL.md is entirely written around a remote service ('https://api.heybossai.com/v1') and requires SKILLBOSS_API_KEY. This is a direct mismatch: local Whisper would not need a remote aggregator API key. The SKILL.md also advertises 50+ remote models and routing, which is not consistent with a purely local-only tool.
Instruction Scope
The instructions direct the agent to make curl calls to heybossai.com endpoints using Authorization: Bearer $SKILLBOSS_API_KEY, download generated assets (curl -sL "$URL" -o <file>), and call many model endpoints. There are references to run.mjs examples in the model docs, but no local binaries or setup instructions are provided. The runtime instructions therefore send user data (e.g., base64 audio) to a third-party API — contradicting the 'local, no API key' claim and raising data-exfiltration / privacy concerns.
Install Mechanism
Instruction-only skill with no install spec or code files to execute. That lowers disk-write risk. However, because it instructs network calls to an external API, lack of an installer doesn't eliminate behavioral concerns.
Credentials
The skill requires a single environment variable SKILLBOSS_API_KEY (declared as primary), which matches the SKILL.md content. The proportionality concern is that the public description explicitly said 'no API key' while runtime requires a key — this is a misleading or inconsistent credential requirement. Requesting a single API key for an aggregator service would be reasonable for remote calls, but it is not justified by the skill's description as presented to users.
Persistence & Privilege
The skill is not always-enabled and is user-invocable; it does not request elevated or persistent privileges, nor does it modify other skills or system settings. Autonomous invocation is allowed by default but is not by itself a red flag 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 openai-whispers - 安装完成后，直接呼叫该 Skill 的名称或使用
/openai-whispers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 openai-whisper skill with extensive multi-model support via SkillBoss API.
- Provides local speech-to-text using the Whisper CLI—no OpenAI API key needed.
- Supports over 50 models for image generation, video generation, text-to-speech, speech-to-text, music creation, chat, web search, document parsing, email, and SMS verification.
- Enables direct API access and smart routing to auto-select providers.
- Includes detailed usage examples and parameters for each task type.
- Requires a single SKILLBOSS_API_KEY for authentication.
元数据
常见问题
Pub Whisper 是什么？
Local speech-to-text with the Whisper CLI (no API key). And also 50+ models for image generation, video generation, text-to-speech, speech-to-text, music, ch... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 311 次。
如何安装 Pub Whisper？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install openai-whispers」即可一键安装，无需额外配置。
Pub Whisper 是免费的吗？
是的，Pub Whisper 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Pub Whisper 支持哪些平台？
Pub Whisper 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 Pub Whisper？
由 ModestyRichards（@modestyrichards）开发并维护，当前版本 v1.0.0。
推荐 Skills