Agent Skills
› wukongrobot/wukongbot
› openai-whisper
openai-whisper
GitHub提供本地 Whisper CLI 工具的使用说明,支持音频转录与翻译。适用于需要离线处理语音文件、生成文本或字幕的场景,无需 API Key,支持多种模型选择以平衡速度与精度。
触发场景
用户请求将音频文件转换为文字
用户需要将语音内容翻译成其他语言
用户询问如何离线处理语音数据
安装
npx skills add wukongrobot/wukongbot --skill openai-whisper -g -y
SKILL.md
Frontmatter
{
"name": "openai-whisper",
"homepage": "https:\/\/openai.com\/research\/whisper",
"metadata": {
"moltbot": {
"emoji": "🎙️",
"install": [
{
"id": "brew",
"bins": [
"whisper"
],
"kind": "brew",
"label": "Install OpenAI Whisper (brew)",
"formula": "openai-whisper"
}
],
"requires": {
"bins": [
"whisper"
]
}
}
},
"description": "Local speech-to-text with the Whisper CLI (no API key)."
}
Whisper (CLI)
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.
版本历史
- 2a72816 当前 2026-08-20 10:14


