Pin It!

Audio transcription doesn’t need the cloud—just your terminal and a pulse.

I was in the middle of editing a grassroots interview for a community radio archive when I hit a wall: the commercial audio transcription service I usually used had just jacked up their prices—and worse, it couldn’t work offline. That was a dealbreaker. Our interviews contain sensitive information from people who rely on anonymity and trust.

As a FOSS advocate, I knew there had to be a better way—something open-source, something I could run in my own terminal, far away from prying servers.

Enter: Whisper CLI.

This lightweight tool brings AI-powered audio transcription to your local machine. No subscriptions. No data leaks. Just your terminal, your audio, and total control.

And in this guide, I’ll show you how to use it.

Download my FREE WhisperAI Cheat Sheet Now!

---

Table of Contents

Pin It!

Pin It!

• Introduction to Whisper CLI
• Why Use Whisper CLI for Audio Transcription?
• Installing Whisper CLI
  • Prerequisites
  • Step-by-Step Installation
    • For Linux/macOS
    • For MacOS:
    • Install Whisper CLI
    • Optional: Install PyTorch
    • Verify Installation
• Basic Usage of Whisper CLI
  • Transcribing Audio Files
  • Translating Audio Files to English
  • Specify Output Format
  • Specify Output Directory
• Language Options in Whisper CLI
• Use Cases for Whisper CLI
• Potential Areas of Expansion
• Handling NumPy Compatibility Issues
  • Downgrade NumPy
• Your Terminal Is Mightier Than the Cloud

Pin It!

---

Introduction to Whisper CLI

Whisper CLI by OpenAI is an automatic speech recognition (ASR) system that excels in audio transcription and translation tasks. This tool supports over 60 languages and provides accurate text conversion from spoken audio. Whisper CLI is ideal for content creators, developers, and businesses looking for a reliable and efficient transcription solution.

For more information about Whisper CLI, check the official GitHub repository.

Pin It!

· · ─ ·𖥸· ─ · ·

Why Use Whisper CLI for Audio Transcription?

• Open Source & Free – No hidden fees, no subscriptions, and fully community-driven.
• Offline Processing – Transcribe audio locally without relying on cloud services.
• High Accuracy – Uses OpenAI’s state-of-the-art speech recognition model.
• Multilingual Support – Transcribe and translate audio in over 100 languages.

· · ─ ·𖥸· ─ · ·

Installing Whisper CLI

Prerequisites:

• Python 3.7 or higher
• pip (Python package installer)

Step-by-Step Installation:

For Linux/macOS:

sudo apt update && sudo apt install python3 python3-pip

For MacOS:

brew install python3

Install Whisper CLI:

Install Whisper CLI directly from its GitHub repository using pip:

pip3 install git+https://github.com/openai/whisper.git

Optional: Install PyTorch

Whisper CLI relies on PyTorch for neural network computations. Install PyTorch for optimized performance:

pip3 install torch torchvision torchaudio

Verify Installation:

After installation, verify it by running:

whisper --help

Pin It!

Basic Usage of Whisper CLI

With Whisper CLI installed, you can start transcribing and translating audio files with simple commands.

Transcribing Audio Files:

To transcribe an audio file to text, use:

whisper path/to/audio.mp3 --task transcribe

Translating Audio Files to English:

Whisper CLI can translate audio from any supported language into English:

whisper path/to/audio.mp3 --task translate

Specify Output Format:

To output transcription in different formats, such as .srt:

whisper path/to/audio.mp3 --output_format srt

Specify Output Directory:

To save the output in a specific directory:

whisper path/to/audio.mp3 --output_dir /path/to/output_directory

For detailed usage, refer to the Whisper CLI documentation.

· · ─ ·𖥸· ─ · ·

Language Options in Whisper CLI

Whisper CLI supports over 60 languages for transcription and translation. Here’s a complete list of supported languages:

To specify a language manually, use:

whisper path/to/audio.mp3 --language [language_code] --task transcribe

· · ─ ·𖥸· ─ · ·

Use Cases for Whisper CLI

Whisper CLI offers a range of applications across various fields:

• Media and Content Creation: Transcribe interviews, podcasts, and generate subtitles.
• Education: Transcribe lectures and aid language learning.
• Business: Generate meeting minutes and improve customer support.
• Legal: Transcribe legal proceedings and documents.

· · ─ ·𖥸· ─ · ·

Potential Areas of Expansion

Whisper CLI has potential for future improvements:

• Real-Time Transcription: Implement live transcription for events and calls.
• API Integration: Develop APIs for cloud-based transcription services.
• Language-Specific Models: Enhance accuracy for specific languages.
• Audio File Format Support: Broaden the range of supported audio formats.
• NLP Integration: Combine with NLP tools for advanced text analysis.

Pin It!

Handling NumPy Compatibility Issues

If you encounter an issue where a module compiled with NumPy 1.x cannot run in NumPy 2.0.1, you need to either downgrade NumPy or rebuild the module. Here’s how to do it:

Downgrade NumPy

Uninstall Current NumPy Version:

pip uninstall numpy

Install Compatible NumPy Version:

pip install 'numpy<2'

· · ─ ·𖥸· ─ · ·

Your Terminal Is Mightier Than the Cloud

Whisper CLI is more than just a transcription tool—it’s a quiet revolution. In a world where most AI services demand your data, your money, and your bandwidth, this open-source gem gives you everything you need for high-quality audio transcription—without giving up your freedom.

You’ve seen how easy it is to install, run, and customize. Whether you’re archiving community stories, documenting interviews, or just tired of clicking around clunky dashboards, Whisper CLI keeps you in control.

If you found this guide useful, there’s more where that came from.

Subscribe to the DevDigest Newsletter for hands-on FOSS tools, practical walkthroughs, and stories from the frontlines of tech for good.