Set up the voice engine

Reading happens on your own computer. This extension talks to a small, free voice engine you run locally; nothing you read is sent anywhere.

1. Install uv

   The Python installer the engine uses. Skip this if uv --version already works.

   macOS / Linux Windows

   curl -LsSf https://astral.sh/uv/install.sh | sh

2. Install the engine

3. Start it, once

   sawt agent install

   Downloads the voice model (about 350MB, one time), then keeps the engine running in the background: it starts by itself when you log in and restarts if it stops. You can close the window when it finishes.

   Rather run it only when you need it? sawt serve works too, as long as that window stays open.