# RHVoice/RHVoice

a free and open source speech synthesizer for Russian and other languages

Repository: https://github.com/RHVoice/RHVoice
Canonical: https://ross.abutalabs.com/products/rhvoice
Homepage: https://rhvoice.org
Language: C++
License: GPL-2.0
License Family: copyleft
Topics: linux, text-to-speech, windows, speech-synthesis, hts, english, brazilian-portuguese, esperanto, georgian, ukrainian, russian, tatar, android, kyrgyz, tts
Last push: 2026-08-10T20:12:51+00:00

## Health v2 (maintenance only)
Score: 91/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 77, longevity 100
- inputs: {"age_days": 5880, "days_push": 23, "days_rel": 155, "gap_med": 11, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1831, forks 270 (observed 2026-08-28T04:05:41.828591+00:00)

## What it is
RHVoice is a free and open-source statistical parametric speech synthesizer (TTS) built on HTS technology, originally for Russian and now supporting many languages including English, Ukrainian, Brazilian Portuguese, and Esperanto. It integrates with standard text-to-speech interfaces such as SAPI5 on Windows, Speech Dispatcher on Linux, and Android TTS APIs, and is widely used by visually impaired users with screen readers like NVDA and Orca.

## Use cases
- give my linux screen reader a free russian voice
- text to speech for android in ukrainian
- use a sapi5 voice with jaws on windows
- nvda addon for multilingual tts voices
- open source speech synthesis for esperanto or tatar
- lightweight tts voices built from statistical models
- tts for languages with poor existing voice support

## When to choose
- you need free, offline TTS voices for Russian or other less-supported languages
- you use a screen reader (NVDA, JAWS, Orca, TalkBack) and need an accessible voice
- you want small-footprint voices on Windows, Linux, or Android

## When to avoid
- you need highly natural, neural-network-quality voices
- you need a cloud-hosted or API-based TTS service
- you need a language not on the supported list and cannot build voice resources

## Facets
- artifact type: application
- maturity: active
- function: tts, speech-recognition, nlp
- domain: speech-processing, accessibility
- platform: windows, cross-platform
- tags: speech-synthesis, hts, screen-reader, russian, multilingual, sapi5, nvda, visually-impaired, natural-language-processing, linux, android

## Member repositories
- RHVoice/RHVoice (main) score 91

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:41.828591+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:19:10.949404+00:00, confidence not recorded.
  - readme: https://github.com/RHVoice/RHVoice (fetched 2026-08-28T04:05:41.828591+00:00, sha e1377be0cae1)
  - homepage: https://rhvoice.org (fetched 2026-08-29T10:57:58.322872+00:00, sha 2e6e1dcee3f7)
  - site_page: https://rhvoice.org/installation (fetched 2026-08-29T10:57:58.325360+00:00, sha df759c263d4e)
- Data as of 2026-08-30T08:39:29.467469+00:00.