|
This version is still in development and is not considered stable yet. For the latest stable version, please use dengjen-nvda 4.x! |
Dengjen Neural Voices for NVDA
This add-on adds neural text-to-speech voices to NVDA. It provides a synthesizer driver for Piper voice models, which run entirely on your own machine, plus a voice manager for downloading and installing voices. An internet connection is needed to download voices, but not to speak with them.
These pages are for developers. To install the add-on and use the voice manager, read the README.
Piper is a fast, local neural text-to-speech system that sounds great and is optimized for low-end devices such as the Raspberry Pi. You can hear what the voices sound like on the Piper voice samples page. Speech is generated by dengjen, a cross-platform Rust engine for neural TTS models.
Requirements
-
NVDA 2026.1 or later.
-
The Microsoft Visual C++ 2015-2022 Redistributable (x64). The speech engine bundled with the add-on is built with MSVC and cannot start without it. If it is missing, the add-on shows a message pointing you to that download; install it and restart NVDA. Most Windows machines already have it.
