RHVoice is a free and open-source speech synthesizer.
RHVoice uses statistical parametric synthesis. It relies on existing open-source speech technologies (mainly HTS and related software).
Voices are built from recordings of natural speech. They have small footprints, because only statistical models are stored on users' computers. And though the voices lack the naturalness of the synthesizers which generate speech by combining segments of the recordings themselves, they are still very intelligible and resemble the speakers who recorded the source material.
Initially, RHVoice could speak only Russian. Now it also supports:
- American and Scottish English
- Brazilian Portuguese
- Esperanto
- Georgian
- Ukrainian
- Kyrgyz
- Tatar
- Macedonian
- Albanian
- Polish
In theory, it is possible to implement support for other languages, if all the necessary resources can be found or created.
If you want to listen to an example of speech synthesis, You can use the TTS service on this page.
RHVoice supports the following platforms:
- Windows (prebuilt binaries is available in documentation)
- GNU/Linux (building instructions and packaging status can be found in "Compiling instructions" section of documentation.
- Android (can be installed thru F-Droid or Google Play
It is compatible with standard text-to-speech interfaces on these platforms: SAPI5 on Windows, Speech Dispatcher on GNU/Linux and Android's text-to-speech APIs. It can also be used by the NVDA screen reader directly (the driver is provided by RHVoice itself).
All prebuild binaries packages, main and legal information and more are available in three languages:
- GitHub Discussions
- Mailing list (Russian)
- IRC channel:
#rhvoiceat irc.libera.chat - Matrix room: #rhvoice:libera.chat