← All projects
Speech & audio

whisper.cpp

A fast, lightweight version of the Whisper speech-to-text model that runs on ordinary computers and phones.

What it does

whisper.cpp is a rebuilt version of OpenAI's Whisper, a model that turns speech into written text. It is written in the C and C++ programming languages with no extra dependencies, which makes it small and quick.

It runs fully offline on Mac, Windows, Linux, iPhone, Android, Raspberry Pi and even in a web browser. It is tuned for Apple Silicon Macs and can also use many kinds of graphics cards, or run on the main processor alone.

It is designed to be easy to build into other apps. The project also includes examples such as a simple offline voice assistant.

Who it's for

Developers building speech-to-text into apps, and technical users who want private, offline transcription.

Can I use it without coding?

With some setup. You build it from source with a few terminal commands and download a model file. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Mac, Windows, Linux, Phone, Web browser
Computer
An ordinary computer is fine
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

  1. Download the project and one of the Whisper speech models.
  2. Give it a 16-bit WAV audio file to get a text transcript.

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (MIT): Very permissive: free to use, change and share, including for business.
  • More on staying safe