RHVoice

RHVoiceGPL-2.0活跃维护

免费开源的语音合成引擎,支持俄语、英语、葡萄牙语等多种语言,可在 Android 和 Linux 上离线把文本转成语音。

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

1.18.5发布于 2026-11-06 18:58 UTC1,857star +1 / 7 天269fork同步于 2026-11-10 11:46 UTC

怎么上手

README 里没有找到可直接复制的安装命令

README 里没有找到可直接复制的安装命令,请到 README 或官方文档查看安装方式。

硬件要求按 README 说明

README 未说明

下载:源码 zip·GitHub Releases(安装包)本站不镜像安装包

项目说明

由 README 自动翻译提炼

开源语音合成器,用统计参数合成多语言语音,体积小且可懂

免费开源的语音合成引擎,支持俄语、英语、葡萄牙语等多种语言,可在 Android 和 Linux 上离线把文本转成语音。

核心能力

  • 基于 HTS 的统计参数合成,只存统计模型
  • 支持俄语、英语、葡萄牙语、世界语、格鲁吉亚语、乌克兰语、吉尔吉斯语、鞑靼语、马其顿语、阿尔巴尼亚语、波兰语
  • 兼容 Windows SAPI5、Linux Speech Dispatcher、Android TTS 接口
  • 提供 NVDA 屏幕阅读器驱动
  • Windows 有预编译二进制,Android 可通过 F-Droid 或 Google Play 安装

容易踩的坑

Linux 需按文档自行编译,README 未给出直接安装命令;Android 需通过 F-Droid 或 Google Play 安装;语音需从录音构建,README 未说明是否需额外下载语音包

内容由模型根据 README 生成,可能不完整或不准确,以官方文档为准。看原文 README

最近发版

5 个版本1.18.5
  1. 1.18.5最新正式版2026-11-06 · 2026-11-06 18:58 UTC

    What's Changed

    New Contributors

    Full Changelog: https://github.com/RHVoice/RHVoice/compare/1.18.4...1.18.5

  2. 1.18.42026-03-31 · 2026-03-31 10:02 UTC
    查看更新说明

    What's Changed

    New Contributors

    Full Changelog: https://github.com/RHVoice/RHVoice/compare/1.18.3...1.18.4

  3. 1.18.32026-03-19 · 2026-03-19 15:52 UTC
    查看更新说明

    What's Changed

    Full Changelog: https://github.com/RHVoice/RHVoice/compare/1.18.2...1.18.3

  4. 1.18.22026-03-11 · 2026-03-11 15:21 UTC
    查看更新说明

    What's Changed

    Full Changelog: https://github.com/RHVoice/RHVoice/compare/1.18.1...1.18.2

  5. 1.18.12026-02-21 · 2026-02-21 17:14 UTC
    查看更新说明

    What's Changed

用户点评

登录用户的真实使用记录,可按版本和硬件筛选
共 0 条

    还没有人点评。第一个说出真实体验的人最有价值。

    README 原文

    未翻译

    RHVoice

    RHVoice is a free and open-source speech synthesizer.

    Features

    Speech synthesis method

    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.

    Supported languages

    Initially, RHVoice could speak only Russian. Now it also supports:

    • American and Scottish English
    • Brazilian Portuguese
    • Esperanto
    • Georgian
    • Ukrainian
    • Kyrgyz
    • Tatar
    • Macedonian
    • Albanian
    • Polish

    In theory, it is possible to implement support for other languages, if all the necessary resources can be found or created.

    Synthesis example

    If you want to listen to an example of speech synthesis, You can use the TTS service on this page.

    Supported platforms

    RHVoice supports the following platforms:

    • Windows (prebuilt binaries is available in documentation)
    • GNU/Linux (building instructions and packaging status can be found in "Compiling instructions" section of documentation.
    • Android (can be installed thru F-Droid or Google Play

    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).

    Documentation

    All prebuild binaries packages, main and legal information and more are available in three languages:

    Community

    Official

    Unofficial