Narrator's voice replace (TTS - Female)

CREDIT

  Inspired by Kasada, Wolfdua, Snk4211, Nolester, Xiaokuii

DESCRIPTION

Sm8zeqKo7TM

aFhK3Z0HDYQ

You are free to use this voice

This mod let TTS (Text-to-speech) AI read Narrator's dialogue, which extracted by STT (Speech-to-text) program

Listen to compare: Samples

>>Girl version<<

>>Male version<<

This is 100% AI's voice, It's 2024. I can make a video of the whole progress for ya'll to withness, if I need to.

The video using High accurary version

All my mods of Narrator's replacement will base on this from now on

This is a 72-hour (couple of weeks using mobile phone) transcribed product, it has been edited to sound as real as possible

Do enjoy, give your comments and maybe, a little donation for my time <3

INSTALLATION

Install with BG3ModManager (enable it, allow it) or manually, it's just a single .pak file

OTHER

STT's script ( Google Colaboratory ):

from google.colab import drive

drive.mount('/content/drive')

!pip install git+https://github.com/openai/whisper.git

!sudo apt update && sudo apt install ffmpeg

from google.colab import drive

drive.mount('/content/drive')

import shutil

import time

# Define the directory containing .wav files

audio_dir = "/content/drive/MyDrive/audios"

# Define the output directory in Google Drive

output_dir = "/content/drive/MyDrive/Narrator_Out_Large"

# Define the completed directory in Google Drive

completed_dir = "/content/drive/MyDrive/Completed/audios"

# Counter for processed files

counter = 0

# Get the total number of .wav files

total_files = len()

# Function to replace any existing file or folder

def replace_existing(path):

if os.path.exists(path):

if os.path.isfile(path):

os.remove(path)

shutil.rmtree(path)

# Create the output and completed directories if they don't exist

for dir in :

if not os.path.exists(dir):

os.makedirs(dir)