TTS Voice Wizard: Speech-to-Text and Text-to-Speech for VRChat Avatars

What TTS Voice Wizard solves, and who it is for

VRChat does not give you a microphone-to-text pipeline out of the box. If you are mute, if you are in a noisy room, or if you simply want your speech to appear as text on your avatar, you need something that captures audio, runs speech recognition, and pushes the result into VRChat. TTS Voice Wizard is that something. The README describes it as an accessibility tool for VRChat, and it also states plainly that it works outside of VRChat. The audience is narrow but clear: Windows users who want their spoken words to show up on an avatar or in the VRChat Chatbox, and who may also want a synthetic voice to speak for them. The repository topics list chatbox, osc, speech-recognition, speech-to-text, text-to-speech, vrchat and vtuber, which matches the feature list in the README: speech-to-text, text-to-speech, translation into over 50 languages, Spotify or browser media display, battery life via XSOverlay, heart rate via Pulsoid or HRtoVRChat_OSC, voice commands for avatar parameters, and interactive counters for VRChat contact receivers. The project is written in C#, licensed MIT, and the last push was on 2026-08-19.

How the speech-to-text-to-OSC path actually works

The mechanism visible from the repository is a single Windows application that sits between your microphone and VRChat. The README states that you can convert your speech-to-text and back to speech through various speech recognition and text-to-speech methods, and that you can send what you say as OSC messages to VRChat to be displayed on your avatar using KillFrenzyAvatarText, Frosty's Billboard, or VRChat's Chatbox. So the flow is: audio in, recognition, optional translation or word replacement, then an OSC message out. The repository layout supports this reading. The solution file is OSCVRCWiz.sln, and the main project directory is OSCVRCWiz, which suggests the OSC sending logic is the core of the app, not an add-on. A separate MoonbaseVoices directory sits at the top level, which is consistent with the README's claim of 100+ voices with customization options. The app also listens rather than only sends: the README documents an OSCListener for tracker and controller battery life, and a VRChatListener for counters tied to contact receivers. That means the app has both an outbound path (your speech to VRChat) and an inbound path (VRChat data back into the app for display). The README does not document the OSC port or address patterns, so anyone integrating a custom avatar should read the linked guides rather than guess.

Installing TTS Voice Wizard and getting text into VRChat

The primary install path is a download from the GitHub releases page. The README's GETTING STARTED section links a zip for v1.7.7.8, but the releases list shows v1.8.0.2 as the most recent release, so check the releases page rather than the README's badge. The README says to read the Quickstart Guide or watch the tutorial video for basic setup. There is also an alternative install via scoop, which the README credits to babo4d. The two commands are shown in the README as follows.

scoop bucket add extras
scoop install extras/tts-voice-wizard

After installing, the first real use is getting your speech to appear in VRChat. The README lists a guide titled How to get Text in VRChat, and it names three display targets: KillFrenzyAvatarText, Frosty's Billboard, and the VRChat Chatbox. Which one you use depends on your avatar, not on the app. If you want your speech spoken aloud rather than displayed, the README points to the Text-to-Speech guide and to VoiceWizardPro for keys. The README does not give a default OSC port or a config file path, so the exact values come from the website guides. The README also notes that the app requires Windows 10 or 11 and that compatibility with older Windows versions is not guaranteed.

Where TTS Voice Wizard breaks down

The most obvious limitation is the platform. The README lists Windows 10/11 as a requirement and says compatibility is not guaranteed with older versions. There is no macOS or Linux build mentioned anywhere in the README. If your streaming or VR setup runs on anything else, this is the wrong tool. The second limitation is documentation placement. The repository README is mostly a set of links to ttsvoicewizard.com and to YouTube videos. The README does not document uninstall steps, rollback, the OSC port, the config file location, or how voice data is stored. That is a real cost: when something stops working, the repository itself will not tell you why. The third limitation is the VoiceWizardPro key. The README links to a guide on getting a key, which implies some voices or features are gated behind that key, but the README does not state which. Anyone evaluating the app for a fully offline or fully free setup should read that guide before assuming everything is available without it. Finally, the README's own demonstration video is described as a bit outdated, so the feature list may not match the current UI.

How it compares to wiring VRChat OSC yourself

The real alternative is not another app of the same shape. It is building the pipeline yourself: run a speech recognition engine, format the text, and send OSC to VRChat's Chatbox or to an avatar parameter. That approach gives you full control over the recognition model, the port, and the message format, and it can run on Linux. What TTS Voice Wizard adds is the assembly. It bundles speech recognition, text-to-speech, translation into over 50 languages, word replacements, voice commands for avatar parameters, Spotify and browser media display, battery life through XSOverlay, heart rate through Pulsoid or HRtoVRChat_OSC, and counters for VRChat contact receivers. Doing all of that yourself is a project, not an afternoon. The trade-off is the opposite of the usual one: you give up portability and transparency in exchange for not having to write the glue. If you only need one feature, such as sending recognized text to the Chatbox, a small script may be less to maintain than a full GUI app. If you need several of the listed features at once, the app is the shorter path.

Maintenance, licence and what an upgrade costs you

The repository is not archived, and the last push was on 2026-08-19. The release history shows v1.8.0 on 2026-05-08, v1.8.0.1 on 2026-05-28, and v1.8.0.2 on 2026-08-19, so releases have been arriving across 2026. The project is MIT licensed, which means you can read, modify and redistribute the C# source, and the licence text is in the repository root as LICENSE. That matters if you want to fork the OSC sending logic into your own tool. It does not mean the app is free of third-party constraints: the README points to Pulsoid, XSOverlay and VoiceWizardPro, and those are separate services with their own terms. The upgrade cost is mostly the cost of a GUI app on Windows. The README does not document a rollback path or a portable mode, so if a new release changes behaviour you are relying on the Discord and the website docs rather than on the repository. Keep the installer for the version you are running if you need to go back.

Editorial conclusion

Adopt TTS Voice Wizard if you are on Windows 10 or 11, already use VRChat with OSC, and want speech-to-text plus text-to-speech in one app. Do not adopt it if you need macOS or Linux, or if you cannot accept that the repository README does not document uninstall or rollback and instead points to the website and Discord. Verify first that your avatar is set up for KillFrenzyAvatarText, Frosty's Billboard or the VRChat Chatbox, and check the Quickstart Guide for the current install steps before you rely on the app for a stream.

Frequently asked questions

Official sources

1. License: MIT
2. Project website
3. README
4. Releases
5. VRCWizard/TTS-Voice-Wizard on GitHub