Piper
A local text-to-speech engine with a web server, developer APIs and trainable voices. It's open source under GPL-3.0.
Piper turns text into spoken audio on local hardware. It's an open-source, GPL-3.0 text-to-speech engine for developers building voice features, accessibility tools and self-hosted AI projects. Speech generation runs locally, giving people a way to add a voice to software they control.
Piper has a command-line interface and a web server, so it can serve different kinds of applications. Developers can also use its Python or C/C++ APIs to build speech into their own software. It uses the embedded eSpeak NG engine to prepare text for speech generation. Voice training is supported for projects that need a voice of their own.
Projects using Piper include Home Assistant, NVDA, Open Voice Operating System and LocalAI. Those examples span spoken home controls, screen reading and AI assistants, and show where a local speech engine can fit. Piper is an engine for producing speech, with interfaces for applications that need to call it.
