Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

openai-whisper — Claude skill: local audio transcription

This skill lets your agent call the Whisper CLI to transcribe audio on your own machine. No API key needed.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add openclaw/openclaw --skill openai-whisper -a claude-code
Open on GitHub

What openai-whisper does

The skill tells the agent how to run whisper on audio files locally. Everything runs on your computer, so recordings never leave it.

Inside is a short instruction with ready commands. whisper /path/audio.mp3 --model medium --output_format txt --output_dir . writes a text file, and whisper /path/audio.m4a --task translate --output_format srt translates speech into subtitles. Models download to ~/.cache/whisper on the first run, so expect that first call to take longer. The --model flag defaults to turbo; smaller models are faster, larger ones more accurate.

The skill checks for the whisper binary on your system, so install it first. If you cannot run local binaries or the audio must stay off your machine, skip this one. Worth adding if you already transcribe from the terminal and want the agent to handle it.

What it helps with

  • transcribe a meeting recording into text
  • generate srt subtitles from a video file
  • translate speech into another language
  • extract text from an m4a file without uploading it

Example prompts for the agent

  • Transcribe `audio.mp3` with the medium model and save the txt to this folder
  • Turn `interview.m4a` into srt subtitles translated to English
  • Run `call.wav` through whisper and show me the text

How to install openai-whisper

1Skills CLI (Vercel)

npx skills add openclaw/openclaw --skill openai-whisper -a claude-code

2Manually: put the files in place

~/.claude/skills/openai-whisper/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/openai-whisper/

From the same set45

The whole set →
summarize openclaw Runs a CLI tool to summarize or transcribe web articles, YouTube videos, podcasts, and local PDF documents directly within your AI assistant. Claude Code CX Codex Cursor +1 26,900installs weather openclaw This skill fetches current conditions and forecasts for a city, region, airport code, or coordinates. Use it to check rain and temperature or plan a trip. Claude Code CX Codex Cursor +1 9,300installs gog openclaw Guides an agent using the gog CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs. Use it when Google Workspace tasks need to run from a terminal. Claude Code CX Codex Cursor +1 8,500installs tmux openclaw Lets an agent work with live tmux sessions: read pane output, send keys and text, wait for a prompt line to show up. Claude Code CX Codex Cursor +1 8,400installs nano-pdf openclaw Edit PDF pages with plain text instructions through the nano-pdf CLI. Useful when you need to fix a typo or swap a heading without leaving your terminal. Claude Code CX Codex Cursor +1 7,100installs skill-creator openclaw A skill for writing, repairing and reviewing other skills. It splits behaviour into branches, sets the frontmatter and sorts resources into folders. Useful once your skill folder gets crowded. Claude Code CX Codex Cursor +1 6,700installs coding-agent openclaw This skill sends large coding tasks to Codex, Claude Code, or OpenCode as background workers. Use it for refactors, PR reviews, and issue-to-PR work. Claude Code CX Codex Cursor +1 6,500installs obsidian openclaw Interacts with Obsidian vaults through the official obsidian CLI. It helps agents read, search, and update notes or tasks without leaving the chat. Claude Code CX Codex Cursor +1 6,400installs

Similar

gws-modelarmor-sanitize-response official googleworkspace This skill sends a model response to Google Model Armor for filtering with a template. Use it to check output before showing it to a user. Claude Code CX Codex Cursor +1 29,500installs marketing-loops coreyhaines31 Sets up a recurring marketing loop an agent runs on a cadence, with a trigger, bounded steps, a self-check and a stop condition. Useful when a task repeats weekly. Claude Code CX Codex Cursor +1 47,200installs typesafe-ai typesafe-ai Guides agents on integrating TypeSafe Decision Models like Jev, answering typed questions about state with calibrated probabilities instead of brittle prompts. Claude Code CX Codex Cursor +1 95,600installs watch bradautomates Analyzes a video from a URL or local path, collects frames and a transcript, then lets the agent answer questions about the footage. Useful for video review inside an IDE. Claude Code CX Codex Cursor +1 17,100installs gemini-api-dev official google-gemini Guides coding agents to write Gemini API code in Python and TypeScript using current SDKs, interaction endpoints, and active models. Claude Code CX Codex Cursor +1 25,100installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. Claude Code 466,719installs media-use heygen-com Finds or generates media for HyperFrames videos, including voiceovers, music, cutouts, and color grades. Stores files locally in assets. Claude Code CX Codex Cursor +1 1,100,000installs

Questions about openai-whisper

How do I install Anthropic-whisper in Claude?

Run npx skills add openclaw/openclaw --skill openai-whisper -a claude-code. The skill file lands at ~/.claude/skills/openai-whisper/SKILL.md. The whisper binary itself is installed separately, for example with brew.

What does openai-whisper do?

It gives the agent instructions for running the Whisper CLI to turn audio into text, subtitles or a translation. All processing happens locally, with no API key.

Which models are available and where do they download?

Models download to ~/.cache/whisper on first run. The default is turbo, and --model lets you pick a smaller one for speed or a larger one for accuracy.

Source text

SKILL.md · MIT 
---
name: openai-whisper
description: "Local speech-to-text with the Whisper CLI (no API key)."
homepage: https://openai.com/research/whisper
metadata:
  {
    "openclaw":
      {
        "emoji": "🎤",
        "requires": { "bins": ["whisper"] },
        "install":
          [
            {
              "id": "brew",
              "kind": "brew",
              "formula": "openai-whisper",
              "bins": ["whisper"],
              "label": "Install OpenAI Whisper (brew)",
            },
          ],
      },
  }
---

# 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/whisper` on first run.
- `--model` defaults to `turbo` on this install.
- Use smaller models for speed, larger for accuracy.

© openclaw · MIT · openclaw/openclaw

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor