Package: wnpp Severity: wishlist Owner: Yauhen Kharuzhy <jek...@gmail.com>
* Package name : rhvoice Version : 0.5.1~pre-20151020 Upstream Author : Olga Yakovleva <yakovleva....@gmail.com> * URL : https://github.com/Olga-Yakovleva/RHVoice * License : LGPL-3+, GPL-3+, BSD-3-clause, MIT, BSL-1.0, LGPL-2.1 Programming Lang: C, C++ Description : free and open source speech synthesizer RHVoice is a open source speech synthesizer with good quality and perfomance. It supports Russian, English, Esperanto and Georgian languages and can be used in text-to-speech systems (with Speech Dispatcher for instance). 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. I plan to prepare package, upload it via sponsor (found already) and maintain by myself.