#118 · Primary category: Speech & Audio
TTS-Voice-Wizard
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)
Project last updated:08/19/26
GitHub Stars
799
Forks
81
Contributors
7
License
MIT
Why we included this project
This is a Windows desktop tool for VRChat users who want what they say to show up as text on their avatar. It takes your microphone input, runs speech-to-text, then sends the transcript through a text-to-speech engine, so you can speak in one voice and be heard in another. The recognized text also goes out as OSC messages to VRChat's chatbox or avatar text systems. On top of that core loop it can translate your speech into dozens of languages, display the currently playing Spotify track, and put heart rate or controller battery data in the chatbox. VTubers and streamers can use it for live captions or voice-driven effects, and since it works outside VRChat as well, it doubles as a general-purpose speech-to-text-to-speech accessibility tool.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
whisper.cpp
Port of OpenAI's Whisper model in C/C++
Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
VibeVoice
Open-Source Frontier Voice AI
voicebox
The open-source AI voice studio. Clone, dictate, create.
TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production