Slip of a Tongue: Whisper Edition

A fork of Slip of a Tongue that uses WhisperLib instead of VoskLib. Put words in list so when players say the word (via mic), a series of commands will be run.

模组 Forge 其他游戏机制

介绍

中文介绍正在准备中，下面暂时显示原文。

🎤 Slip of a Tongue: Whisper Edition

Slip of a Tongue: Whisper Edition allows players to trigger server-side commands using their actual voice. Powered by the high-accuracy WhisperLib engine, your spoken words are processed locally and sent to the server for secure execution.

🔥 What’s New in Whisper Edition?

High Accuracy: Powered by OpenAI’s Whisper, it understands natural speech, accents, and fast talkers far better than the old VoskLib.

Smart Noise Filtering: Automatically ignores background music, coughs, and non-speech sounds like [MUSIC] or *laughing*.

Zero Lag: Audio processing happens on a separate thread, so your FPS stays buttery smooth.

🛠 Installation

Client-Side (Required)

Install WhisperLib.

Install Slip of a Tongue: Whisper Edition.

Download a Model: Open the WhisperLib config in-game and download a model (we recommend base.en for the best performance-to-speed ratio).

Server-Side (Required)

Install Slip of a Tongue: Whisper Edition (WhisperLib is not required on the server).

Configure your word list in the server’s config folder.

⚙️ Command Syntax

The server-side configuration uses a specific format to map voice triggers:

word:[command1, command2, %player%]Text to narrate

word: The keyword or phrase to detect.
\[…\]: List of commands (no / needed).
%player%: Automatically replaced by the speaker’s name.
Text to narrate: The message sent to chat upon success.

Example: jump:[effect give %player% levitation 2 10]See you later!

🔒 Security & Privacy

Local Processing: Speech-to-text happens entirely on your machine. No audio data ever leaves your computer.
Server-Side Validation: The server only executes commands that are explicitly defined in its configuration, preventing players from spoofing unauthorized commands.

📜 Credits

Engine: WhisperLib by MeroSsSany.
Original Inspiration: VoskLib and Slip of a Tongue.
Speech Model: Powered by OpenAI’s Whisper.

[\[ Whisper Edition Branch \]](https://github.com/MeroSsSany/slipofthetongue/tree/Whisper-Edition) [\[ Original GitHub Branch \]](https://github.com/MeroSsSany/slipofthetongue/)