Whisper CLI: local speech-to-text transcription
Transcribe audio locally with the Whisper CLI, turning recordings into text without needing an API key.
Requirements
- The whisper command-line tool must be available. It can be installed with brew using the openai-whisper formula, which provides the whisper binary, and no API key is required.
How to use
Use the whisper command to transcribe audio locally.
Models download to ~/.cache/whisper on first run.
On this install, --model defaults to turbo.
Use smaller models for speed and larger models for accuracy.
Install OpenAI Whisper via brew (formula openai-whisper) to get the whisper binary.
To transcribe a file to plain text in the current directory, run: whisper /path/audio.mp3 --model medium --output_format txt --output_dir .
To translate an audio file and produce subtitles, run: whisper /path/audio.m4a --task translate --output_format srt
Source: openclaw/openclaw and its contributors. License: MIT.
Copyright (c) 2026 OpenClaw Foundation
Translation and editorial adaptation by ClawCases.
>Resources
>Related Use Cases
Apple Notes CLI
Manage Apple Notes directly from the terminal with the memo CLI: create, view, edit, delete, search, move notes between folders, and export notes to HTML or Markdown.
Automate the macOS UI with the Peekaboo CLI
Use Peekaboo to inspect the macOS UI, act on the intended target, and verify the result. The examples use v4 syntax; check the current documentation and the installed command's help, and for older versions follow that version's help.
Generate audio spectrograms and feature visualizations with songsee
Generate spectrograms and multi-panel audio feature visualizations from audio files using the songsee command-line tool.