Agent Skills
› spinabot/brigade
› openai-whisper
openai-whisper
GitHub本地使用 Whisper CLI 进行音频转录和翻译，无需 API 密钥。支持多种音频格式及输出格式，可根据需求选择模型大小以平衡速度与精度。
触发场景
需要本地处理音频文件转文字
需要将语音内容翻译成其他语言
安装
npx skills add spinabot/brigade --skill openai-whisper -g -y
SKILL.md
Frontmatter
{
"name": "openai-whisper",
"homepage": "https:\/\/openai.com\/research\/whisper",
"metadata": {
"brigade": {
"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
- db99206 当前 2026-07-05 10:59
