Plain-AyI
← All projects
Speech & audio

Speech To Speech

A voice assistant you talk to out loud, built from open models that run on your own computer.

New this week

What it does

Speech To Speech is a voice assistant made from open AI models. You speak, pause, and it answers through your speakers. It listens for when you talk, writes down what you said, thinks of a reply and then speaks it.

The README says it runs entirely on your computer, with no API key or cloud service needed. The models download on first use, and after that it can work offline. Each part can be swapped for a different model, including hosted ones.

Developers can also connect their own apps to it, because it speaks the same language as OpenAI's Realtime voice service.

Who it's for

Developers and tinkerers building voice assistants, robots or talking characters, and anyone curious about private voice AI.

Can I use it without coding?

With some setup. You install it with Python and start it from the command line. 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 on your computer, then install Speech To Speech with Python's package installer.
  2. Start it in local mode and wait a few minutes while the models download the first time.

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