Menü
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Drive a headed Chromium via the agent-browser CLI — open/click/type/hover/scroll/screenshot/snapshot/eval/pdf/network-route. Use this for any web interaction; no native browser tool is exposed.
Search, install, and verify Debian or Ubuntu packages with apt-get in the container.
Search the web using DuckDuckGo. No API key required. Supports instant answers and HTML scraping modes. Privacy-focused search alternative.
Control the Linux desktop GUI using xdotool, wmctrl, dogtail, and scrot. Provides a window list, an accessibility-tree viewer (with coordinates) for finding buttons and text fields, a thin xdotool wrapper for actuating them, and a launcher helper that enables accessibility for Electron/Chromium apps.
This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses DuckDuckGo's search API to return results in clean, formatted output (text, markdown, or JSON). Use for research, fact-checking, finding recent information, or gathering web resources.
Placeholder task skill.
| name | openai-whisper-api |
| description | Transcribe audio via OpenAI Audio Transcriptions API (Whisper). |
| homepage | https://platform.openai.com/docs/guides/speech-to-text |
| metadata | {"clawdbot":{"emoji":"☁️","requires":{"bins":["curl"],"env":["WHISPER_API_KEY"]},"primaryEnv":"WHISPER_API_KEY"}} |
Transcribe an audio file via OpenAI’s /v1/audio/transcriptions endpoint.
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a
Defaults:
whisper-large-v3-turbo for Groq/vveai
URLs and whisper-1 otherwise. Override with --model NAME or
WHISPER_MODEL.<input>.txt{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --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
{baseDir}/scripts/transcribe.sh /path/to/video.mp4 --srt --out /tmp/captions.srt
For --srt / --vtt the script always asks the API for verbose_json
and assembles SRT/VTT locally, so the same flag works against providers
(e.g. Groq) that don't emit SRT natively.
Required env:
WHISPER_API_KEY — your key. The helper falls back to OPENAI_API_KEY
only when WHISPER_API_KEY is unset.Optional env:
WHISPER_BASE_URL — endpoint root, defaults to
OPENAI_BASE_URL when set, otherwise https://api.groq.com/openai/v1.
Include /v1 in the URL.WHISPER_TIMEOUT_SECONDS — request timeout; defaults to 300 seconds.