القائمة
Transcribe audio via OpenAI Audio Transcriptions API (Whisper); Don't use if you want local/offline transcription; prefer openai-whisper.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Manage Apple Notes via the `memo` CLI on macOS (create, view, edit, delete, search, move, and export notes). Use when a user asks OpenClaw to add a note, list notes, search notes, or manage note folders; Don't use for markdown/linked notes (obsidian), collaborative docs (notion), or tagged research (bear-notes).
Create, search, and manage Bear notes via grizzly CLI; Don't use for quick system capture (apple-notes), plain markdown files (obsidian), or collaborative docs (notion).
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control; Don't use for simple one-off shell commands; use exec tool directly.
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs; Don't use for non-Gmail email; prefer himalaya for IMAP/SMTP accounts.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language). Don't use for Gmail/Google Workspace; prefer gog
iMessage/SMS CLI for listing chats, history, watch, and sending; Prefer bluebubbles if available; this is the fallback iMessage CLI.
| name | openai-whisper-api |
| description | Transcribe audio via OpenAI Audio Transcriptions API (Whisper); Don't use if you want local/offline transcription; prefer openai-whisper. |
| homepage | https://platform.openai.com/docs/guides/speech-to-text |
| metadata | {"openclaw":{"emoji":"☁️","requires":{"bins":["curl"],"env":["OPENAI_API_KEY"]},"primaryEnv":"OPENAI_API_KEY"}} |
Transcribe an audio file via OpenAI’s /v1/audio/transcriptions endpoint.
openai-whisper for local/offline transcription.{baseDir}/scripts/transcribe.sh /path/to/audio.m4a
Defaults:
whisper-1<input>.txt{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model whisper-1 --out /tmp/transcript.txt
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --language en
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --prompt "Speaker names: Peter, Daniel"
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a --json --out /tmp/transcript.json
Set OPENAI_API_KEY, or configure it in ~/.openclaw/openclaw.json:
{
skills: {
"openai-whisper-api": {
apiKey: "OPENAI_KEY_HERE",
},
},
}