RHVoice

From ArchWiki

RHVoice is a multilingual speech synthesizer. It uses statistical parametric synthesis and relies on existing open-source speech technologies (mainly HTS and related software).

Installation

Install the rhvoice package. Also install necessary #Languages and #Voices.

Languages

Initially, RHVoice could speak only Russian. But now it supports many other languages.

Available languages list you can get by command:

$ pacman -Ss rhvoice-lang
Package name Language
rhvoice-language-albanian Albanian
rhvoice-language-brazilian-portuguese Portuguese
rhvoice-language-english English
rhvoice-language-esperanto Esperanto
rhvoice-language-georgian Georgian
rhvoice-language-kyrgyz Kyrgyz
rhvoice-language-macedonian Macedonian
rhvoice-language-polish Polish
rhvoice-language-russian Russian
rhvoice-language-tatar Tatar
rhvoice-language-ukrainian Ukrainian

Voices

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.

Available voices list you can get by command:

$ pacman -Ss rhvoice-voice
Package name Language Note
rhvoice-voice-hana Albanian
rhvoice-voice-leticia-f123 Portuguese
rhvoice-voice-alan English Scottish English
rhvoice-voice-bdl
rhvoice-voice-clb
rhvoice-voice-evgeniy-eng Evgeniy Chebatkov (StandUp comedian, voice actor)
rhvoice-voice-lyubov Lyubov Sablina (teacher at the language center "Lingua Belle")
rhvoice-voice-slt
rhvoice-voice-spomenka Esperanto
rhvoice-voice-natia Georgian
rhvoice-voice-azamat Kyrgyz
rhvoice-voice-nazgul
rhvoice-voice-kiko Macedonian Developed by LouderPages
rhvoice-voice-suze Developed by Branislav Gerazov
rhvoice-voice-magda Polish
rhvoice-voice-natan
rhvoice-voice-aleksandr Russian Aleksandr Karlov (TV and radio host, audiobook reader).
The current version of the HQ voice has a higher quality than the previous version, their sound is different, so the new version is temporarily separated into a separate voice to collect feedback. This version may contain issues that are not present in the original voice. Since the speech base is open, we will be happy for your participation in improving the voice.
rhvoice-voice-aleksandr-hq
rhvoice-voice-anna
rhvoice-voice-arina Arina Syukkya (event organizer, designer)
rhvoice-voice-artemiy Artemiy Lebedev (designer, blogger, traveler)
rhvoice-voice-elena
rhvoice-voice-evgeniy-rus Evgeniy Chebatkov (StandUp comedian, voice actor)
rhvoice-voice-irina
rhvoice-voice-mikhail Mikhail Sokolov (news anchor on Autoradio)
rhvoice-voice-pavel Pavel Klyachenko (psychologist, tiflopsychologist)
rhvoice-voice-tatiana Tatiana Kruk (host of broadcasts on «Tiflo Info»)
rhvoice-voice-victoria Natalya Arsenyeva (radio host and author of the travel blog "I was there")
rhvoice-voice-vitaliy Vitaliy Chuvaev (brand voice of Russia Today TV channel)
rhvoice-voice-yuriy Yuriy Zaborovsky (Soviet and Russian actor, audiobook reader)
rhvoice-voice-talgat Tatar
rhvoice-voice-anatol Ukrainian
rhvoice-voice-marianna Marianna Firtka (radio presenter)
rhvoice-voice-natalia
rhvoice-voice-volodymyr Volodymyr Beglov (journalist, radio host, lecturer)

Synthesis example

You can listen to examples of speech synthesis for different voices here and here.

Configuration

Configuration file located at: /etc/RHVoice/RHVoice.conf.

File format and available settings are detail described in official documentation.

Speech-dispatcher

RHVoice includes module for speech-dispatcher.

Everything should work out of the box without additional settings. But if you want to set RHVoice as the default synthesizer for speech-dispatcher, use the spd-conf utility or change the configuration file manually (if you want to change per-user configuration, edit ~/.config/speech-dispatcher/speechd.conf instead):

/etc/speech-dispatcher/speechd.conf
# -----OUTPUT MODULES CONFIGURATION-----
...
DefaultModule rhvoice
...

Usage

If configuration you made is correct, the following commands will allow you to start the synthesis (for voice bdl):

$ echo "test" | RHVoice-test -p "bdl"
$ spd-say -o rhvoice -y bdl "test"

Dictionaries

User dictionaries must be created in the /etc/RHVoice/dicts/ directory, for example, for the English language: /etc/RHVoice/dicts/English/.

See also