Clone Yourself with Synthesia and Eleven Labs

AI Tool Kit for making an AI Video and Voice Clone of yourself

How to make an AI video and voice clone

AI Tool Kit for creating an avatar that looks and moves like yourself.

1. Synthesia (making a Video Avatar of the real person)

2. Eleven Labs (Audio / Voice of the real person)

Steps to create a 'Digital Human' - a Clone of yourself

These latest AI tools generate a clone make it hard to tell the difference between what's real and what's fake.

Step 1: Make a video recording of yourself AI avatar using Synthesia.

For a professional and real looking avatar, you need to record video of yourself in a studio with a green screen as the background.

The recorded video should have you doing a series of head movements and also lips movements for audio - so you have to read read through a pre-written script such as:

"Positive thinking will help you believe in yourself and fill you with self-esteem and confidence."

Step 2: After that, head over to an Audio Studio where you will recorded another script for about an hour.

"My name is Karen Henderson and I hereby consent to this audio recording to create a custom voice."

You will then send the Audio file to Synthesia who will use it as 'training data' and run it through their AI neural networks.

Synthesia's Audio cloning produced; "Hello, Karen. I hope you you don't mind if I call you Karen? Do you? "

If this voice isn't the best, you can use ElevenLabs Tools which will produced something better, especially if you upload a couple of hours worth of clear recordings.

Both Synthesia and ElevenLabs work similarly. Type in anything and AI Avatar of me just says it right back.

Synthesia is aimed at companies that want to make internal videos. It charges at least $1,000 to create a custom avatar.

Creating a voice clone with ElevenLabs is $5 a month.

Once you have your voice cloned, enter a script into Synthesia, put a green screen behind your avatar and export it.

Synthesia has already started to improve a lot of this in beta versions of its avatars, for example, you can now nod your head.

Once you have your avatar, your can enter text into Synthesia and export talking videos of your avatar using Synthesis.