$ loading_
Local speech-to-text with the Whisper CLI (no API key).
复制安装指令，让 AI 自动完成配置 · 推荐新手
请帮我安装 askskill 上的 "openai-whisper" 技能： 1. 下载 https://raw.githubusercontent.com/openclaw/openclaw/main/skills/openai-whisper/SKILL.md 2. 保存为 ~/.claude/skills/openai-whisper/SKILL.md 3. 装好后重载技能，告诉我可以用了
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 srtNotes
~/.cache/whisper on first run.--model defaults to turbo on this install.Summarize CodexBar local cost logs by model for Codex or Claude, including current or full breakdowns.
Edit PDFs with natural-language instructions using the nano-pdf CLI.
Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.
Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.
Notion CLI/API for pages, Markdown content, data sources, files, comments, search, Workers, and raw API calls.
Search meme templates, suggest formats, and generate local or hosted image memes.