Whisper

by OpenAI

OpenAI's speech-to-text model, the reference for open speech recognition.

110.3 k stars GitHub MIT FreeOpen sourceOpen weightsLocal

View on GitHub →

What it does

Transcribes dozens of languages and translates into English
Six model sizes, from lightest to most accurate
Exports text and subtitles (SRT, VTT) in one command

Install it

Requirements: Python and FFmpeg installed.

Install with pip

pip install -U openai-whisper

Transcribe a file

whisper audio.mp3 --model turbo

The prompt for your agent

Paste it into your coding agent: it checks the requirements and installs it for you.

Claude CodeCodexCursorGemini CLIopencode

Prompt

Install Whisper (https://github.com/openai/whisper) on my machine.
1. Check the requirements: Python and FFmpeg installed. If anything is missing, tell me before installing anything.
2. Follow the official method:
- Install with pip: pip install -U openai-whisper
- Transcribe a file: whisper audio.mp3 --model turbo
3. Check that it works, then explain how to launch it and where to start.

Always review what your agent is about to run, especially install commands.