MINECRAFTBIBLE
Loading...
Punishes players for speaking forbidden words
CensorCraft is a Forge Minecraft mod that listens to your voice with Simple Voice Chat and punishes you for saying forbidden words.
See the wiki for setup instructions!
To test it, hop into a single-player world and say "boom" into your microphone (with Simple Voice Chat enabled and your microphone unmuted).
When you first try to join a world, you'll be asked to download a model. Then when in-game, your audio feed is transcribed using this model. If it detects you spoke a forbidden word, all sorts of punishment may be incurred, such as:
Punishments are set by the server admin, configurable in the server config file.
A: Models are what CensorCraft uses to transcribe your voice. Because models are too large to be bundled with the mod, CensorCraft downloads the model at runtime to your client config folder. All models are hosted safely by the HuggingFace community.
A: Transcription accuracy is bound to the model. Although the server admin can increase transcription accuracy with a bigger and better model, transcription isn't always perfect. If you are getting particularly unusual results, delete the model from your client config folder and rejoin the world to install the model again. If it persists, open an issue in the GitHub repo.
A: You may see a "CensorCraft is far behind" message if transcription is taking too long. This caused by one of two factors: either you're not using the GPU for transcription, or your machine isn't powerful enough to run this mod.
If Vulkan is found, transcription is handled by your GPU to increase transcription speed. If not, it'll default to using the CPU (which is almost always slower). Make sure you have Vulkan installed and ensure your graphics drivers are up to date!
You can disable Use GPU in the client config to use your CPU if it's faster, or play with the Latency bar in your client config menu to get the best results.