仅支持 Windows 10/11,旧版 Windows 兼容性不保证;把 TTS 音频送进麦克风需要按文档配置虚拟音频线;部分高级音色和 DeepGram 转写需订阅 VoiceWizardPro 才能使用
TTS-Voice-Wizard
VRCWizardMIT活跃维护把语音识别成文字再转成语音,并通过 OSC 消息把文本推到 VRChat 头像聊天框显示,还能播报当前歌曲。
Speech to Text to Speech. Song now playing. Sends text as OSC messages to VRChat to display on avatar. (STTTS) (Speech to TTS) (VRC STT System) (VTuber TTS)
下载 Releases 中的 TTSVoiceWizard-v1.7.7.8-x64.zip 解压运行;或用 scoop:scoop bucket add extras && scoop install extras/tts-voice-wizardREADME 只说明需要 Windows 10/11,未提及显存、CPU 或 GPU 型号要求
把语音转文字再转语音并通过 OSC 推到 VRChat 显示在头像上的 Windows 桌面工具
把语音识别成文字再转成语音,并通过 OSC 消息把文本推到 VRChat 头像聊天框显示,还能播报当前歌曲。
核心能力
- 语音经语音识别转文字后再合成语音播放
- 用 OSC 把说的话发送到 VRChat 头像或 Chatbox 显示
- 支持把语音翻译成 50 多种语言
- 内置 100 多种音色可选并支持自定义
- 显示 Spotify 或浏览器当前播放歌曲
容易踩的坑
- v1.8.0.3pre-release2026-10-12 · 2026-10-12 15:54 UTC
查看更新说明
v4 ElevenLabs models added
- v1.8.0.2最新正式版2026-08-19 · 2026-08-19 19:58 UTC
Fix for Spotify Refresh Token error.
Relevant documentation: https://developer.spotify.com/blog/2026-06-18-refresh-token-expiration
- v1.8.0.1pre-release2026-05-28 · 2026-05-28 02:01 UTC
查看更新说明
- Fix for Azure Dragon voices not working with Voice Wizard Pro.
- UI fix
- v1.8.02026-05-08 · 2026-05-08 16:35 UTC
查看更新说明
- Fix for Weilbyte endpoint TikTok TTS error
- Voiceforge option removed (deprecated)
v1.7.7.9
- Fix for saving Azure Dragon HD voices as presets
- Spotify reminder message updated
- More supported languages for DeepL:
- Afrikaans
- Albanian
- Arabic
- Armenian
- Azerbaijani
- Bosnian
- Bulgarian
- Cantonese
- Catalan
- Croatian
- Galician
- Hebrew
- Hindi
- Icelandic
- Irish
- Kazakh
- Latin
- Macedonian
- Malay
- Marathi
- Nepali
- Persian
- Punjabi
- Serbian
- Swahili
- Tamil
- Telugu
- Thai
- Urdu
- Uzbek
- Vietnamese
- Welsh
- v1.7.7.9pre-release2026-04-05 · 2026-04-05 14:57 UTC
查看更新说明
- Fix for saving Azure Dragon HD voices as presets
- Spotify reminder message updated
- More supported languages for DeepL:
- Afrikaans
- Albanian
- Arabic
- Armenian
- Azerbaijani
- Bosnian
- Bulgarian
- Cantonese
- Catalan
- Croatian
- Galician
- Hebrew
- Hindi
- Icelandic
- Irish
- Kazakh
- Latin
- Macedonian
- Malay
- Marathi
- Nepali
- Persian
- Punjabi
- Serbian
- Swahili
- Tamil
- Telugu
- Thai
- Urdu
- Uzbek
- Vietnamese
- Welsh
用户点评
登录用户的真实使用记录,可按版本和硬件筛选还没有人点评。第一个说出真实体验的人最有价值。
TTS-Voice-Wizard
Features
Use TTS Voice Wizard's accessibility features to improve your VRChat experience (it works outside of VRChat too!)
🎙️ You can convert your Speech-to-Text and back to Speech through various Speech Recognition and Text-to-Speech methods
💬 You can send what you say as OSC messages to VRChat to be displayed on your avatar using KillFrenzyAvatarText/Frosty's Billboard or VRChats Chatbox
🌐 The app can translate your speech from one language to over 50 other supported languages
🔊 There are 100+ different voices with various customization options so you can pick a voice that best suits you
🎵 Display the current song you are listening to on Spotify or via your browser
🔋 Display tracker and controller battery life in conjunction with XSOverlay
❤️ Use in conjuntion with Pulsoid or HRtoVRChat_OSC to enable you to display your heartrate in VRChat's Chatbox
🗣️ Control VRChat avatar parameters with voice commands
🫵 Display customizable and interactive counters for amount of times a VRChat contact receiver has been touched
📹 For a more detailed look at the app's features, check out the Demonstration Video (although it's a bit outdated)
GETTING STARTED
Download TTS Voice Wizard
-
Please read the Quickstart Guide or watch the Tutorial Video for instructions on how to set up the basic features of TTS Voice Wizard.
Alternative Installation Method
Thanks to babo4d TTS Voice Wizard also can be installed via scoop with the following commands:
scoop bucket add extrasscoop install extras/tts-voice-wizard
Requirements
- Windows 10/11 (compatibility not guarenteed with older version of Windows)
GitHub Wiki Table of Contents
Quick Start Guide
- Tutorial Video
- Installation
- Speech-to-Text and Text-to-Speech
- 🗨️ How to get Text in VRChat
- 🖱️ Can I set hotkey on my VR controllers or mouse for Speech to Text?
- 🎵 Spotify / Windows Media Integration for VRChat
- 📹 OBS Text for Streaming and Recording Videos
Additional Guides
- 🌐 How to Translate my Words?
- 🔑 How to get a VoiceWizardPro Key?
- 🗣️ How to do Voice Commands?
- 🫵 How to setup VRChat Counters?
- 🔀 How to do Word Replacements
- 💓 How to set up Heartrate for VRChat Chatbox?
- 🔋 How to set up Tracker/Controller Battery Life for VRChat Chatbox?
Need Help / Have Questions / Wanna make suggestions?
- Join the Discord Server
What comes next?
- Check the Trello page to see what features will be coming out next!
Support the Project
- Leave me a Github Star ⭐ (it's free) or
🔑 Unlock VoiceWizardPro Benefits!
Subscribe to Ko-Fi or Patreon and experience a world of powerful features that will transform your TTS and translation experience:
-
✨ Instant Access to Premium Voices: Enjoy hundreds of voices from leading cloud services, including:
- Microsoft Azure
- Amazon Polly
- Google Cloud
- IBM Watson
-
🌍 Multilingual Magic: Translate your voices into 70+ supported languages, talk to your friends from all over the world
-
🎤 Crystal-Clear Transcriptions: Gain access to speech recognition through DeepGram's Nova-2 model, the fastest and most accurate speech-to-text API.
Your subscription not only enhances your capabilities but also supports future development:
- 💪 Empower Ongoing Development: Your contribution assists in server upkeep, covers character costs from premium APIs, and fuels future software innovations.
Ready to elevate your TTS game? Dive into VoiceWizardPro now! For detailed insights, explore our VoiceWizardPro Docs.
Unlock the power of VoiceWizardPro today! 🚀
Partners
- TalaTora - TalaTora the talented tiger VTuber, check them out on twitch
Credits
- @RavenNovaa - New logo art by @RavenNovaa on twitter, check them out :)
- CoreOSC - Sending / recieving OSC data (modified for sending UTF8)
- octokit.net - Github Update Notifier
- AutoUpdater.NET - Auto Updater for .NET applications
- Sharptalk - .NET wrapper for the FonixTalk TTS engine.
- tiktok-tts - Tiktok voices made possible by Weilbyte's Tiktok TTS endpoint
- KillFrenzyAvatarText (KAT) - A text display system designed to be used on VRChat Avatars
- Frosty's Billboard - Frosty's billboard is a container for the KAT allowing you to have a speech bubble in your hand
- WindowsMediaController - Windows Media Package
- WhisperNet - C# wrapper for whisper.cpp
- ZAPSPLAT - Sound effects obtained from https://www.zapsplat.com