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

openai-whisper-api — Claude skill: audio transcription

Runs audio through the OpenAI Audio Transcriptions API and returns text or JSON. Useful when you want a call or voice note transcribed without leaving the agent.

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

What openai-whisper-api does

The skill hits /v1/audio/transcriptions with curl. Everything lives in one script, transcribe.sh, which takes a file path and flags. Defaults are gpt-4o-transcribe and output next to the input as .txt.

Swap models with --model: gpt-4o-transcribe, gpt-4o-mini-transcribe, gpt-4o-transcribe-diarize, whisper-1. Diarize mode adds speaker labels; the script sends chunking_strategy=auto and refuses --prompt. Set the spoken language with --language, hint at names with --prompt, switch output with --json.

You need OPENAI_API_KEY, either in the environment or in the OpenClaw config ($OPENCLAW_CONFIG_PATH, default ~/.openclaw/openclaw.json). curl and node must be present too. The hosted API caps uploads at 25 MB and accepts mp3, mp4, mpeg, mpga, m4a, wav, webm. Longer recordings need splitting first. Worth installing if you already use OpenAI and want transcription wired into your agent instead of a separate console call.

What it helps with

  • turn a recorded meeting into text
  • label who said what with diarize
  • get a transcript as JSON for downstream parsing
  • pin the language so recognition stops guessing
  • pass speaker names to the model via prompt

Example prompts for the agent

  • Transcribe /path/to/audio.m4a and save the text next to it
  • Run audio.ogg through gpt-4o-transcribe-diarize and give me JSON
  • Transcribe audio.m4a with --language en

How to install openai-whisper-api

1Skills CLI (Vercel)

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

2Manually: put the files in place

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

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

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 openai-whisper openclaw This skill lets your agent call the Whisper CLI to transcribe audio on your own machine. No API key needed. Claude Code CX Codex Cursor +1 7,100installs 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

Similar

hindsight-docs vectorize-io This skill gives AI agents Hindsight documentation for architecture, APIs, configuration, and SDKs. Use it when adding Hindsight memory to an agent. Claude Code CX Codex Cursor +1 9,100installs 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 mcp-builder official anthropics This skill walks through building an MCP server in TypeScript or Python, from reading the protocol spec to writing tests and evaluation questions. Claude Code Claude.ai 130,949installs subagent-driven-development Jesse Vincent This skill runs an implementation plan through fresh subagents for independent tasks and reviews each result. Use it for multi-step work in one session. Claude Code CX Codex 237,746installs orchestration stablyai Coordinates supervised Orca workers with task DAGs, decision gates, and threaded messages. Fits workflows that split work across multiple agents. Claude Code CX Codex Cursor +1 349,200installs

Questions about openai-whisper-api

How do I install Anthropic-whisper-api in Claude?

Run npx skills add openclaw/openclaw --skill openai-whisper-api -a claude-code. The skill lands in ~/.claude/skills/openai-whisper-api/SKILL.md.

What does openai-whisper-api do?

It sends an audio file to the OpenAI Audio Transcriptions API and returns text or JSON. Pick the model with --model.

What do I need before using it?

An OPENAI_API_KEY plus curl and node installed. The key can sit in the OpenClaw config or in your environment.

Source text

SKILL.md · MIT 
---
name: openai-whisper-api
description: "OpenAI Audio Transcriptions API via curl; gpt-4o-transcribe, mini, diarize, or whisper-1."
homepage: https://platform.openai.com/docs/guides/speech-to-text
metadata:
  {
    "openclaw":
      {
        "emoji": "🌐",
        "requires": { "bins": ["curl", "node"], "env": ["OPENAI_API_KEY"] },
        "primaryEnv": "OPENAI_API_KEY",
        "install":
          [
            {
              "id": "brew",
              "kind": "brew",
              "formula": "curl",
              "bins": ["curl"],
              "label": "Install curl (brew)",
            },
          ],
      },
  }
---

# OpenAI transcriptions API

Transcribe audio through `/v1/audio/transcriptions`. Set `OPENAI_BASE_URL` for an OpenAI-compatible proxy or local gateway.

## Quick start

```bash
{baseDir}/scripts/transcribe.sh /path/to/audio.m4a
```

Defaults:

- Model: `gpt-4o-transcribe`
- Output: `<input>.txt`

## Useful flags

```bash
{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model gpt-4o-transcribe --out /tmp/transcript.txt
{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model gpt-4o-mini-transcribe
{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model gpt-4o-transcribe-diarize --json
{baseDir}/scripts/transcribe.sh /path/to/audio.ogg --model whisper-1
{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
```

Notes:

- Supported upload formats include `mp3`, `mp4`, `mpeg`, `mpga`, `m4a`, `wav`, `webm`.
- 25 MB upload limit on the hosted API.
- Use diarize for speaker labels; script sends `chunking_strategy=auto` and rejects `--prompt`.

## API key

Set `OPENAI_API_KEY`, or configure it in the active OpenClaw config file (`$OPENCLAW_CONFIG_PATH`, default `~/.openclaw/openclaw.json`). Optionally set `OPENAI_BASE_URL`:

```json5
{
  skills: {
    "openai-whisper-api": {
      apiKey: "OPENAI_KEY_HERE",
    },
  },
}
```

© 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