RHVoice
A free, open-source speech synthesizer for Russian and other languages, used with screen readers and desktops.
These buttons open the developer's own site, repository or store listing in a new tab. wares.gg does not host downloads.
About RHVoice
RHVoice is a text-to-speech engine that started with Russian and now covers other languages. It uses statistical parametric synthesis built on existing open-source speech technologies, so its voices are light and quick rather than as natural as large neural models.
It suits screen reader users and anyone who needs a local speech engine. The repository includes packaging for Android and a Snap package for Linux.
Strengths
- Runs locally without a network connection
- Lightweight statistical parametric synthesis
- Strong support for Russian alongside other languages
Limitations
- Sounds less natural than neural text-to-speech
- Language and voice coverage is limited compared with commercial engines
Details
- Pricing
- FreeFree and open source.
- License
- Open source, license not stated
- Developer
- The RHVoice contributors
- Platforms
- Linux, Android
- How it runs
- Downloadable app
- Account
- Not required
- Works offline
- Yes
- Best suited for
- Screen reader users who want a free local voice, especially for Russian
- Categories
- AI voice
- Last verified
- Added
- Sources
Alternatives to RHVoice
Compare allSoftware that can replace RHVoice for an important use case, and what changes if you switch.
Piper
A fast neural text-to-speech engine that runs locally, even on modest hardware like a Raspberry Pi.
Piper is a GPL-3.0 neural engine that runs locally even on a Raspberry Pi, likely sounding more natural, but it has no graphical interface and targets integration use.
MeloTTS
An open-source multilingual text-to-speech engine from MIT and MyShell.ai with a command line and web UI.
MeloTTS is an MIT-licensed local engine with several English accents and five other languages, though it needs Python or Docker setup and development has slowed.
Kokoro
Small, fast open-weight text-to-speech model you can run locally.
Kokoro is a small Apache-licensed neural model that runs fast locally on Windows, macOS and Linux, but it is used as a Python library without a GUI.
Coqui TTS
Deep learning toolkit for training and running text-to-speech models.
Coqui TTS is an MPL-2.0 toolkit with pretrained models in many languages and training support, but it needs deep learning familiarity and has seen no update since mid-2024.
Similar software
Related functionality, not necessarily a direct replacement.
Balabolka
A free Windows program that reads text aloud with installed voices and saves it as audio files.
Speech Note
A Linux app for offline speech-to-text, text-to-speech and machine translation using local models.
Voice Dream Reader
A text-to-speech reading app that turns PDFs, ebooks, documents and web pages into audio.
NaturalReader
A text-to-speech app that reads documents, PDFs, web pages and scanned text aloud with AI voices.
Speaches
A self-hosted, OpenAI API-compatible server for local speech-to-text, translation and text-to-speech models.
