OHF-Voice/piper1-gpl

Health v2 · maintenance only

Adoption not part of the score

5287 stars · 507 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

library · maturity active

tts speech-recognition cli http-server machine-learning speech-processing artificial-intelligence accessibility self-hosted python cpp cross-platform cli text-to-speech neural-tts local-inference phonemization espeak-ng voice-training home-assistant offline-tts python-api http-api web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="OHF-Voice/piper1-gpl")