Plain-AyI
← All projects
Speech & audio

Whisper

Turns speech in audio or video into accurate written text, in dozens of languages.

Research-backed

What it does

Whisper is a speech-recognition model from OpenAI. Give it a recording, such as a meeting, interview, podcast or voice note, and it writes out what was said.

It understands many languages and accents and can also translate speech into English. Because it's free and open, it powers a lot of transcription and subtitle apps.

Like any AI, it can occasionally make things up, especially during long silences, so important transcripts are worth a quick check.

Who it's for

Journalists, researchers, students and anyone who needs transcripts or subtitles. It's also a building block for developers.

Can I use it without coding?

With some setup. Runs from the command line. Many free apps bundle it with a simple interface. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Mac, Windows, Linux
Computer
Works best on a powerful computer or one with a graphics card (GPU)
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

  1. Install Python and the free tool ffmpeg on your computer.
  2. Install Whisper using Python's package installer.
  3. Run Whisper on an audio file and it writes out what was said.

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

Where people are talking about it