Translate your voice in real time so VRChat users speaking another language can read it in chat.
See translated captions of what other VRChat users are saying to you.
Automatically pause translation when you mute your mic to save API costs.
| finalsiren1/syncvrc | 0marildo/imago | agentlexi/agent-lexi | |
|---|---|---|---|
| Stars | 3 | 3 | 3 |
| Language | Python | Python | Python |
| Setup difficulty | moderate | easy | moderate |
| Complexity | 2/5 | 2/5 | 4/5 |
| Audience | general | general | vibe coder |
Figures from each repo's GitHub metadata at analysis time.
Requires your own paid API key from a translation provider like Gemini, DeepL, or OpenAI.
SyncVRC is a real-time voice translation tool built specifically for VRChat, a virtual reality social platform where people meet and interact as avatars. The problem it solves is the language barrier: when you are in a virtual room with someone who speaks a different language, normal conversation is impossible. SyncVRC listens to microphone input, converts speech to text using Faster-Whisper, a local speech recognition library, and sends that text to a cloud translation service, such as Gemini, DeepL, or OpenAI, which translates it and displays the result in VRChat's chatbox. Translation works in both directions. Outgoing mode translates what you say and sends it to the chatbox. Incoming mode captures audio from other users through desktop audio and displays a translation on your screen. Both can run at the same time. When you mute your microphone inside VRChat, the tool detects that mute state through VRChat's OSC system, a local communication protocol the game exposes, and automatically pauses translation, avoiding wasted API calls. The tool requires you to supply your own API key from whichever translation service you choose. It stores that key only on your local machine and does not send it to any server run by the developer, and it does not collect or store your voice data either. Paid API keys are recommended because free tier keys have strict rate limits that can cause translations to pause or skip mid conversation. Audio processing settings, including recognition accuracy, silence detection timing, and maximum recording duration, are adjustable to match how you speak. Supported languages include English, Japanese, Chinese, Korean, Spanish, Russian, French, German, Portuguese, and Thai. The tool has known limits: because translation depends on cloud APIs, network problems or rate limits can cause delays or skipped sentences, and the Whisper speech recognition model can occasionally mishear words or invent phrases when the room is noisy or several people are talking at once. It is licensed under MIT.
A real-time voice translation tool for VRChat that turns spoken microphone audio into another language's text inside the game's chat.
Mainly Python. The stack also includes Python, Faster-Whisper, VRChat OSC.
Use freely for any purpose, including commercial use, as long as you keep the copyright notice.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly general.
This repo across BitVibe Labs
Verify against the repo before relying on details.