Clone your voice in 5 minutes!
Oct 29, 2019 · 2 min read

I want to show you an excellent library to clone your voice. I mean that machine could read a text using your voice!
Let's start!
In this article, which I am using code from the repository :
and his forked version(for CPU):
Its video will show you what it’s all about.
Steps to run minimal example(with supported CPU)
#terminal
#you could find requirements.txt in this repo
https://github.com/fuwiak/medium/tree/master/5minutesvirtualenv work
source work/bin/activate
pip3 install -r requirements.txt
Download this file and unpack:
http://www.openslr.org/resources/12/train-clean-100.tar.gz
After unpacking you should see a directory with name LibriSpeech
Assuming that directory LibriSpeech is in Desktop:
#terminalgit clone https://github.com/shawwn/Real-Time-Voice-Cloning
cd Real-Time-Voice-Cloning
python demo_toolbox.py -d ~/Desktop/LibriSpeech/train-clean-100/
After its steps, you should see something like this:

After recording own voice(button Record) you should see something like this:

To read the text “Welcome to the toolbox …” push Synthesize and vocode.
Video with sample voice:
That's all folks! In any case, I look forward to feedback.

