← 返回 Skills 市场
Openai Whisper 1.0.0
作者
Patryk Czubiński
· GitHub ↗
· v1.0.0
1404
总下载
0
收藏
52
当前安装
1
版本数
在 OpenClaw 中安装
/install openai-whisper-1-0-0
功能描述
Local speech-to-text with the Whisper CLI (no API key).
安全使用建议
Before installing, make sure you are comfortable installing the Homebrew openai-whisper package and storing downloaded Whisper models locally. Treat transcripts and output directories as sensitive if the source audio contains private information.
功能分析
Type: OpenClaw Skill
Name: openai-whisper-1-0-0
Version: 1.0.0
The skill bundle describes the installation and usage of the legitimate OpenAI Whisper CLI for local speech-to-text. The `SKILL.md` file provides standard `brew` installation instructions for `openai-whisper` and example commands for local audio transcription. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, prompt injection attempts against the agent, or any other indicators of malicious intent. All described actions are consistent with the stated purpose of the skill.
能力评估
Purpose & Capability
The stated purpose, local speech-to-text with the Whisper CLI and no API key, matches the documented whisper transcription and translation commands.
Instruction Scope
Instructions are limited to user-directed examples for specific audio files and do not include hidden automation, prompt manipulation, credential access, destructive commands, or unrelated workflows.
Install Mechanism
The skill declares a Homebrew install of the openai-whisper formula and requires the whisper binary; this is coherent with the purpose but relies on an external package source.
Credentials
Runtime access is proportionate to local transcription: reading user-specified audio files and writing transcript output where the user directs.
Persistence & Privilege
The only disclosed persistence is Whisper model files downloaded to ~/.cache/whisper on first run; there is no evidence of autostart behavior, background workers, elevated privilege, or credential/session handling.
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-whisper-1-0-0 - 安装完成后，直接呼叫该 Skill 的名称或使用
/openai-whisper-1-0-0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.
- Provides local speech-to-text transcription using the Whisper CLI.
- Supports multiple models, with default set to "turbo" for this install.
- Includes usage examples for transcription and translation tasks.
- No API key required; models are downloaded locally as needed.
元数据
常见问题
Openai Whisper 1.0.0 是什么？
Local speech-to-text with the Whisper CLI (no API key). 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1404 次。
如何安装 Openai Whisper 1.0.0？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install openai-whisper-1-0-0」即可一键安装，无需额外配置。
Openai Whisper 1.0.0 是免费的吗？
是的，Openai Whisper 1.0.0 完全免费（开源免费），可自由下载、安装和使用。
Openai Whisper 1.0.0 支持哪些平台？
Openai Whisper 1.0.0 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 Openai Whisper 1.0.0？
由 Patryk Czubiński（@czubi1928）开发并维护，当前版本 v1.0.0。
推荐 Skills