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 English
- Brazilian Portuguese
- Esperanto
- Georgian
- Ukrainian
- Kyrgyz
- Tatar
- Macedonian
- Albanian
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 here)
- GNU/Linux (building instructions can be found here. You can also look at packaging status.)
- Android (can be installed thru F-Droid or Google Play you can also download an APK consult this file)
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).
The main library is distributed under LGPL v2.1 or later. But it relies on MAGE for better responsiveness. MAGE is distributed under GPL v3 or later, so the combination is under GPL v3 or later. If you want to use the library in your program under GPL v2 or LGPL, compile the library without MAGE.
The following restrictions apply to some of the voices:
All voices from RHVoice Lab's site are distributed under the
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Public License
You can send a request for integration of voice into any product to the laboratory's e-mail address. If the approval is given by the speaker and our team you will get the appropriate permission.
Permission is hereby granted to use, copy, distribute and modify the product on condition that the product or its derivatives are not used commercially: you are not allowed to sell the product or its derivatives.
Regarding commercial use of the voice or any other use not listed here contact the developer acting as a representative of the rights holder.
E-mail: rsbs@yandex.ru
Copyright (c) 2013 - 2018 Beqa gozalishvili, Olga Yakovleva, Vladimer urdulashvili
The Georgian voice can be used free of charge only by individuals for personal use.
Individuals can download voice from official sources of the project and use it for example with screen reading software or with software that can read text aloud.
Individuals can also redistribute the voice among other individuals by putting it on the network, portable devices or in any other way.
It is prohibited to copy, modify, distribute, sell or use this voice by Organizations and manufacturers for inclusion in their products or for any other use. To use the Georgian voice for such purposes, organizations and manufacturers must agree on the details with the copyright holders:
- Beqa Gozalishvili beqaprogger@gmail.com
- Vladimer Urdulashvili vladimerurdulashvili@gmail.com
Copyright (C) 2018 - 2020 Olga Yakovleva, Fernando H. F. Botelho
The voice is distributed under the Creative Commons Attribution-ShareAlike 4.0 International Public License.
See the documents in the licenses/voices subdirectory for more details.