← 返回 Skills 市场
12416
总下载
12
收藏
80
当前安装
1
版本数
在 OpenClaw 中安装
/install local-whisper
功能描述
Local speech-to-text using OpenAI Whisper. Runs fully offline after model download. High quality transcription with multiple model sizes.
安全使用建议
Install only if you are comfortable with the uv/pip dependency setup and the initial Whisper model download/cache size. Consider pinning package versions or using a lockfile, and verify the intended command wrapper because the documentation names scripts/local-whisper while the reviewed bundle contains scripts/transcribe.py.
功能分析
Type: OpenClaw Skill
Name: local-whisper
Version: 1.0.0
The skill bundle provides local speech-to-text functionality using OpenAI Whisper. The `SKILL.md` clearly outlines its purpose, usage, and setup, including legitimate dependencies like `ffmpeg` and Python libraries `openai-whisper` and `torch` from trusted sources (download.pytorch.org). The `scripts/transcribe.py` script correctly implements the transcription logic without any signs of data exfiltration, malicious execution, persistence, or prompt injection against the agent. The only network activity is the expected initial download of Whisper models by the `openai-whisper` library, which is consistent with the 'offline after model download' description.
能力评估
Purpose & Capability
The artifacts match the stated purpose: SKILL.md describes local speech-to-text and scripts/transcribe.py loads a Whisper model, transcribes a user-supplied audio file, and prints text or JSON.
Instruction Scope
Use is user-directed and scoped to an existing audio file; the documentation examples reference scripts/local-whisper, while the bundle contains scripts/transcribe.py, which is a packaging/usability mismatch rather than a security issue.
Install Mechanism
Setup uses a local uv virtual environment and installs click, openai-whisper, and torch from external package sources without pinned versions; this is expected for Whisper but should be reviewed for supply-chain hygiene.
Credentials
The ffmpeg requirement, local model files, and initial model download are proportionate to offline speech-to-text; no credentials, broad filesystem indexing, unrelated network calls, or account access are shown.
Persistence & Privilege
The artifacts show no background service, privilege escalation, destructive action, autonomous persistence, or credential/session handling beyond expected local dependency and model caches.
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 local-whisper - 安装完成后，直接呼叫该 Skill 的名称或使用
/local-whisper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 local-whisper: local speech-to-text using OpenAI Whisper, fully offline after model download.
- Supports multiple model sizes for different speed/quality needs: tiny, base (default), small, turbo, large-v3.
- Includes options for language selection, timestamps, JSON output, and quiet mode.
- Provides clear setup instructions using uv-managed Python virtual environment.
- Requires ffmpeg for audio processing.
元数据
常见问题
Local Whisper 是什么？
Local speech-to-text using OpenAI Whisper. Runs fully offline after model download. High quality transcription with multiple model sizes. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 12416 次。
如何安装 Local Whisper？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install local-whisper」即可一键安装，无需额外配置。
Local Whisper 是免费的吗？
是的，Local Whisper 完全免费（开源免费），可自由下载、安装和使用。
Local Whisper 支持哪些平台？
Local 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 Local Whisper？
由 araa47（@araa47）开发并维护，当前版本 v1.0.0。
推荐 Skills