Openai Whisper

Skill Verified Active

Local speech-to-text with the Whisper CLI (no API key).

Purpose

To provide highly accurate and private speech-to-text transcription locally, without relying on external APIs or requiring an API key, by leveraging the Whisper CLI.

Features

Local speech-to-text transcription
No API key required
Leverages Whisper CLI
Supports multiple Whisper models
Configurable output formats and directories

Use Cases

Transcribing audio files locally for privacy
Converting audio to text for further processing
Translating audio from other languages
Utilizing advanced speech recognition without cloud costs

Non-Goals

Providing cloud-based transcription services
Requiring an API key for operation
Handling real-time streaming transcription (focus is on file-based processing)

Documentation

info:READMEThe README.md is very large and primarily describes the OpenClaw framework, with minimal specific information about the Whisper CLI skill itself.

Installation

npx skills add steipete/clawdis

Runs the Vercel skills CLI (skills.sh) via npx — needs Node.js locally and at least one installed skills-compatible agent (Claude Code, Cursor, Codex, …). Assumes the repo follows the agentskills.io format.

Quality Score

Verified

99 /100

Analyzed about 19 hours ago

Trust Signals

Last commitabout 19 hours ago

GitHub owner steipete

Stars371.6k

Downloads 4.6M

LicenseMIT

Websiteopenclaw.ai

Status

View Source

Similar Extensions

Whisper

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

Skill

Orchestra-Research