Repolode
Submit
OHF-Voice

OHF-Voice/piper1-gpl

A fast, local neural text-to-speech engine that uses espeak-ng for phonemization, installable via pip.

Open-source alternative to:Amazon PollyGoogle Cloud Text-to-Speech

View on GitHub
Stars
5,946
Forks
579
Open issues
149
Last commit
4 days ago

What is it?

Piper is a neural text-to-speech engine that runs locally on the machine, so text is converted to speech without sending it to a cloud service. It embeds espeak-ng for phonemization, the step that turns text into phonemes before the neural model generates audio.

The project can be installed with pip as piper-tts and offers several ways to use it: a command-line interface, a web server with an HTTP API, a Python API, and a C/C++ API through libpiper. Voices are distributed separately, and the repository includes documentation for training new voices and for building the project manually.

Piper is aimed at developers who need offline speech output, such as voice assistants, accessibility tools, or applications running on modest hardware. Home Assistant and several community projects use it as their speech backend.

Key features

  • 01Runs fully locally without a cloud service.
  • 02Uses espeak-ng for text-to-phoneme conversion.
  • 03Installable with pip as piper-tts.
  • 04Provides a command-line interface, HTTP server, Python API and C/C++ API.
  • 05Includes documentation for training new voices.

Use cases

  • Adding offline speech output to a voice assistant or smart home system.
  • Building screen-reader or accessibility features that run without internet access.
  • Generating narration audio from text in scripts or batch jobs.
  • Embedding speech synthesis in a C/C++ application through libpiper.

Quick start

  1. 1

    Install Piper from PyPI with pip

    pip install piper-tts

Things to know

  • The README does not document a usage example beyond installation, so you must consult the linked docs to run it.
  • Training new voices and building manually are covered only by separate documentation pages.

Topics

#text-to-speech#tts#speech-synthesis#offline#onnx#python#espeak-ng

FAQ

What is piper1-gpl?
A fast, local neural text-to-speech engine that uses espeak-ng for phonemization, installable via pip. Piper is a neural text-to-speech engine that runs locally on the machine, so text is converted to speech without sending it to a cloud service. It embeds espeak-ng for phonemization, the step that turns text into phonemes before the neural model generates audio.
Is piper1-gpl free to use? What license does it have?
piper1-gpl is open source under the GPL-3.0 license. Check the license terms before using it in commercial products.
Is piper1-gpl still maintained?
Actively maintained. The last commit to piper1-gpl was on Oct 17, 2026.
What can I use piper1-gpl for?
Adding offline speech output to a voice assistant or smart home system. Building screen-reader or accessibility features that run without internet access. Generating narration audio from text in scripts or batch jobs. Embedding speech synthesis in a C/C++ application through libpiper.
How do I install piper1-gpl?
Install Piper from PyPI with pip: pip install piper-tts
Where can I get piper1-gpl?
The source code and installation instructions are on GitHub: https://github.com/OHF-Voice/piper1-gpl

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects