🎯

openai-whisper-api

🎯Skill

from steipete/clawdis

What it does

Transcribes audio files to text using OpenAI's Whisper API, supporting multiple audio formats and customizable output options.

📦

Part of

steipete/clawdis(48 items)

openai-whisper-api

Installation

npm installInstall npm package

npm install -g openclaw@latest

git cloneClone repository

git clone https://github.com/openclaw/openclaw.git

pnpmRun with pnpm

pnpm install

📖 Extracted from docs: steipete/clawdis

Need more details? View full documentation on GitHub →

11Installs

AddedFeb 4, 2026

View on GitHub Back to Skills

Skill Details

SKILL.md

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

Overview

# OpenAI Whisper API (curl)

Transcribe an audio file via OpenAI’s /v1/audio/transcriptions endpoint.

Quick start

```bash

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

```

Defaults:

Model: whisper-1
Output: .txt

Useful flags

```bash

{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

```

API key

Set OPENAI_API_KEY, or configure it in ~/.openclaw/openclaw.json:

```json5

{

skills: {

"openai-whisper-api": {

apiKey: "OPENAI_KEY_HERE",

}

```

More from this repository10

🎯

gog🎯Skill

Manages Gmail, Calendar, Drive, Contacts, Sheets, and Docs via CLI with OAuth-based Google Workspace interactions.

🎯

weather🎯Skill

Retrieves current weather and forecasts for any location using free services, with multiple output formats and no API key required.

🎯

summarize🎯Skill

Quickly summarizes URLs, local files, and YouTube links using AI models with flexible extraction options.

🎯

coding-agent🎯Skill

Runs coding agents like Claude Code or Codex in bash with PTY support, enabling programmatic control and background processing.

🎯

mcporter🎯Skill

Streamlines interaction with MCP servers through CLI, enabling listing, configuration, authentication, and direct tool calls via HTTP or stdio.

🎯

apple-reminders🎯Skill

Manages Apple Reminders via CLI, enabling listing, adding, editing, completing, and deleting tasks with flexible date and list filtering.

🎯

gifgrep🎯Skill

Searches and downloads GIFs from Tenor/Giphy with a CLI/TUI, enabling preview, extraction, and easy sharing.

🎯

nano-pdf🎯Skill

Edits PDFs using natural language instructions, allowing precise page-level modifications with simple CLI commands.

🎯

obsidian🎯Skill

Automates interactions with Obsidian vaults, enabling searching, creating, moving, and managing Markdown notes via obsidian-cli.

🎯

peekaboo🎯Skill

Automates macOS UI interactions by capturing screens, targeting elements, driving input, and managing apps via a powerful CLI tool.