Plain-AyI
← All projects
Speech & audio

WhisperLiveKit

Live speech-to-text you run yourself, with speaker labels and translation as people talk.

Research-backedNew this week

What it does

WhisperLiveKit turns speech into text in real time, as someone is speaking. You run it on your own computer or server and open a web page to start talking.

Its makers explain that normal Whisper models are built for complete recordings, so this project uses newer research methods to handle live audio without cutting words off. It can also tell speakers apart and translate between many languages.

It offers web connections that copy the style of popular transcription services, so other apps can use it, and it supports several users at once.

Who it's for

Developers and tinkerers who want private, live transcription for meetings, captions or apps.

Can I use it without coding?

With some setup. It's installed with Python and started from the command line, then used in a web browser. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Mac, Windows, Linux, Server
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 WhisperLiveKit with Python's package installer.
  2. Start the server, choosing a model and your language.
  3. Open the local web page it shows and start talking.

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 (Apache-2.0): Permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it