Skip to content
local-ai

Piper

Voice & audio Intermediate Open source Free

A fast, lightweight text-to-speech engine designed to run offline on low-resource hardware, right down to a Raspberry Pi. It is the default local voice for Home Assistant, with many voices across a range of languages.

Strengths

  • Very fast and light, runs offline on modest hardware
  • A wide range of voices and languages
  • Well established, and the standard TTS in Home Assistant

Weaknesses

  • Voices sound less natural than the newest neural TTS models
  • The original repository was archived in October 2025, with development moving to a GPL-3.0 fork
  • Less expressive control than models built for emotion and style

At a glance

Licence
GPL-3.0
Pricing
Free
Platforms
Linux, macOS, Windows
GPU required
No

Links

Works with

Entry last verified 30 July 2026.