Piper

Free

Fast, local neural TTS optimised for the Raspberry Pi.

LightweightOpen-SourceOn-Device

Overview

Piper is a fast, local neural TTS system designed to run well even on a Raspberry Pi 4. It ships with a large library of pre-trained voices across many languages. As the default voice for Home Assistant, it is a top pick for private, offline speech.

What makes Piper special?

Focus: Fast on-device synthesis.
Availability: Free & Open-Source (MIT).
Use cases: Home automation, accessibility, and offline devices.

Visit official site

Related free models

Chatterbox

A lightweight, fast TTS model built on LLaMA.

Dia

A 1.6B parameter TTS model from Nari Labs.

Kokoro

An 82M parameter TTS model by Hexgrad.

Back to directory