🎙️ Openai Whisper 1.0.0 — 语音转文字
v1.0.0使用Whisper CLI进行本地语音转文字（无需API密钥）。
0· 742·37 当前·48 累计
by 安全扫描
OpenClaw
安全
high confidence该技能是围绕本地Whisper CLI的仅指令包装器：需求、安装和指令与其声明的目的一致，不请求额外凭证或意外权限。
评估建议
此技能一致：它只期望本地'whisper'二进制文件并提供本地转录示例。安装前，验证Homebrew公式来源（确认来自可信源），准备可能较大的模型下载（将存储在~/.cache/whisper下），并仅在信任的音频文件上运行CLI。...详细分析 ▾
✓ 用途与能力
Name/description (local Whisper CLI) matches the declared requirement (whisper binary) and examples in SKILL.md. No unrelated credentials, services, or paths are requested.
ℹ 指令范围
SKILL.md only instructs running the whisper CLI on local audio files and notes that models download to ~/.cache/whisper on first run. That behavior is expected for local transcription, but it means the tool will download and store model files to disk and perform network activity to fetch models — users should expect large downloads and local storage use.
ℹ 安装机制
Install uses a Homebrew formula (openai-whisper) which is a common and low-risk mechanism. The SKILL metadata does not specify the tap or formula source; users should verify the brew formula origin to ensure it's from a trusted repository before installing.
✓ 凭证需求
No environment variables, credentials, or config paths are required. This is proportionate for a local CLI wrapper.
✓ 持久化与权限
Skill is not always-enabled and does not request elevated or persistent privileges. It does not modify other skills or system-wide settings.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv1.0.02026/2/19
- 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.
● 无害
安装命令 点击复制
官方npx clawhub@latest install openai-whisper-1-0-0
镜像加速npx clawhub@latest install openai-whisper-1-0-0 --registry https://cn.clawhub-mirror.com
技能文档
Use whisper to transcribe audio locally.
Quick start
whisper /path/audio.mp3 --model medium --output_format txt --output_dir .whisper /path/audio.m4a --task translate --output_format srt
Notes
- Models download to
~/.cache/whisperon first run. --modeldefaults toturboon this install.- Use smaller models for speed, larger for accuracy.
数据来源：ClawHub ↗ · 中文优化：龙虾技能库
OpenClaw 技能定制 / 插件定制 / 私有工作流定制
免费技能或插件可能存在安全风险，如需更匹配、更安全的方案，建议联系付费定制