# OHF-Voice/piper1-gpl

Fast and local neural text-to-speech engine

Repository: https://github.com/OHF-Voice/piper1-gpl
Canonical: https://ross.abutalabs.com/products/piper1-gpl
Language: C++
License: GPL-3.0
License Family: copyleft
Last push: 2026-08-22T07:10:02+00:00

## Health v2 (maintenance only)
Score: 86/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 98, longevity 37
- inputs: {"age_days": 523, "days_push": 11, "days_rel": 18, "gap_med": 20, "n_releases_24m": 8}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5287, forks 507 (observed 2026-08-28T04:09:14.186514+00:00)

## What it is
Piper is a fast, fully local neural text-to-speech engine that embeds espeak-ng for phonemization and ships with a CLI, HTTP web server, Python API, and C/C++ library. It supports training custom voices and is used by projects like Home Assistant and NVDA for offline speech synthesis.

## Use cases
- convert text to speech offline without cloud services
- add a local TTS voice to Home Assistant
- make a screen reader like NVDA speak with neural voices
- serve text-to-speech over HTTP for other apps
- train a custom voice for a low-resource language
- embed speech synthesis in a C++ or Python application

## When to choose
- you need fast, private, offline text-to-speech with no cloud dependency
- you want a TTS engine with CLI, HTTP server, and Python/C++ APIs in one package
- you need to train custom voices, including for low-resource languages
- you're building voice assistants or accessibility tools that run locally

## When to avoid
- you need cloud-hosted TTS with managed scaling
- you want a managed SaaS speech service with billing and SLAs
- you need speech recognition rather than synthesis
- you require a non-GPL license for redistribution

## Facets
- artifact type: library
- maturity: active
- function: tts, speech-recognition, cli, http-server, machine-learning
- domain: speech-processing, artificial-intelligence, accessibility, self-hosted
- platform: python, cpp, cross-platform, cli
- tags: text-to-speech, neural-tts, local-inference, phonemization, espeak-ng, voice-training, home-assistant, offline-tts, python-api, http-api, web-server

## Member repositories
- OHF-Voice/piper1-gpl (main) score 86

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:14.186514+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:59:14.776667+00:00, confidence not recorded.
  - readme: https://github.com/OHF-Voice/piper1-gpl (fetched 2026-08-28T04:09:14.186514+00:00, sha a73f57602007)
- Data as of 2026-08-30T08:39:29.467469+00:00.