Cloning the Wendigos' voice

Wendigos Voice Cloning (Lethal Company mod)

Masked has learned to copy your friends' voices. Can you tell who's real and who's fake?

In order for this mod to work properly, it must be installed in all players.

Here's a video I made to present this mod.

The second video presents this mod in real time.

Disclaimer.

If you are not using Elevenlabs, this mod loads an external binary (about 350 MB) from my github and locally loads an AI model to generate audio clips of masked people. The external binary is 350 MB and the voice clone model is 1.75 GB.

Privacy.

Your voice is cloned entirely locally at runtime. This means that (1) your audio clones are not stored, cloning occurs at runtime, and (2) all processing occurs locally on your machine. It is not externally transmitted. Only created audio clips are exchanged between players.

When you use Elevenlabs, everything is stored in your account.

Initial configuration (not real-time)

If you're using Elevenlabs, pre-clone the votes of all players.

Enable mod in Wendigos.cfg. Optionally, enable Elevenlabs and add the API key and voice ID. Also, be sure to install the language and add a custom voice (see the "Bonus Features" section).

(Only for local AI models - Elevenlabs users are already disabled.) When you first start the game, you will be prompted to record multiple voice replicas. The currently selected microphone is displayed.

If the selected microphone is not the one you want to use, click Close, set the microphone in Settings, and restart the game.

Controls

'R' starts recording.

'Q' stops recording.

'N' displays the following sound.

If your working language is not English, say what you want in this step and then press "Q".

When you stop recording or exit the voice line list, the mode will start generating voice lines.

This step can take a long time. When the generation is complete, the game will notify you!

The first time this happens, the mod will load the sound model (1.75 GB) into the Wendigos MOD folder. Since this model is already loaded, subsequent generation will be much faster.

If you make a mistake and need to record the audio again, quit the game and set "New player sample audio saved?" to true in the Thunderstone configuration "BepInEx/config/Wendigos.cfg".

Bonus opportunities

Custom voice string.

Don't like the default voice string? You can customize what Masked can say in different categories of behavior by editing the file below:

BepInEx/config/Wendigos/player_sentences/player0_chasing_sentences.txt

BepInEx/config/Wendigos/player_sentences/player0_idle_sentences.txt

BepInEx/config/Wendigos/player_sentences/player0_nearby_sentences.txt

New sentences are separated by a new line; AI can be forced to say anything.

Each player can have their own voice string, corresponding to what they say.

Mask enhancements.

This mod removes the mask and zombie hands from the mask, allowing it to better fool the player. The player's clothes will also be emulated.

Eleven Labs.

Players can use Elevenlabs to clone their voice. This gives much better results and can be more deceptive for the mask. To use this feature, all client voices must already be cloned by Elevenlabs. Everyone can use the same api key, but each player needs a unique voice identifier.

Reaction in real time with Azure and ChatGPT (experimental)

Allows masked people to react to player expressions in real time. This feature does not support push-to-talk.

What you need.

Eleven Labs Subscription ($5+)

 Buy as many credits as you like on your profile in [Billing] - [Add Payment Method]. These loans do not expire at the end of the month.

Then go back to your profile -> User API keys -> View project API keys, create a new project, create a new key with the project API key, save it, and enter the ChatGPT API key in wendigos.cfg.

If you can't find the API key, see here: https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key.  

Configuration Settings

Configure all API keys (Elevenlabs, Azure, ChatGPT).

Set the voice ID to Elevenlabs.

Set the Azure region as the newly selected region.

Set General -> Enable mod. and Experimental -> Realtime Responses to true.

Add your name to the Your Name field.

Advanced Settings

Optimize Eleven Labs for speed: Accelerates sound production at the cost of losing most of your voice emotion. The general style and emotionality of speech are reduced.

Speech Probability: The probability that Masked will play a predefined voice line.

Possible problems.

The audio line is out of sync.

Players hear different voices (rarely, but can occur due to jumps in delay).

Writing out of buffer results in unity errors (the generated strings are too large).

Your computer doesn't have enough storage space for models and audio lines.

Each player stores voice clone models (1.75 GB), sound samples (~10 MB), and audio tracks (<500 KB each) locally.

FREQUENTLY ASKED QUESTIONS.

What languages does this mod support?

This mod uses XTTSv2 and supports 17 languages: English (en), Spanish (es), French (fr), German (de), Italian (it), Portuguese (pt), Polish (pl), Turkish (en), Russian (ru), Dutch (nl), Czech (cs), Arabic (ar), Chinese (zh-cn), Japanese (ja), Hungarian (hu), Korean (hko), Hindi (hi).

Eleven Labs is available in 32 languages. For more information, see https://elevenlabs.io/languages.