Have you ever wondered how those deepfakes of celebrities like Mr. Beast were able to clone their voices? Well, those people use voice cloners like the F5-TTS model in order to do this, and in this article, you’ll learn that it’s actually not that hard!
How it works:
- You record yourself speaking a sentence
- The AI trains itself on your voice (F5-TTS Model)
- You input text for the AI to say in your voice
- The workflow outputs a playable MP3 file, saying something in your voice
Table of Contents
Software
We will use ComfyUI, a free AI image and video generator. You can use it on Windows, Mac, or Google Colab.
Think Diffusion provides an online ComfyUI service. They offer an extra 20% credit to our readers.
Read the ComfyUI beginner’s guide if you are new to ComfyUI. See the Quick Start Guide if you are new to AI images and videos.
Take the ComfyUI course to learn how to use ComfyUI step by step.
Step-by-step guide
Step 0: Update ComfyUI
Before loading the workflow, make sure your ComfyUI is up to date. The easiest way to do this is to use ComfyUI Manager.
Click the Manager button on the top toolbar.
Select Update ComfyUI.
Restart ComfyUI.
Step 1: Download the workflow
Download the ComfyUI JSON workflow:
Drag and drop the JSON file to ComfyUI.
Step 2: Install missing nodes
If you see red blocks, you don’t have the custom node that this workflow needs.
Click Manager > Install missing custom nodes, and install the missing nodes.
Restart ComfyUI.
Step 3: Install F5-TTS
If the previous step doesn’t work, you need to clone the custom node’s repository manually
Go to your terminal and type in these commands under the ComfyUI installation folder:
- cd custom_nodes
- git clone https://github.com/niknah/ComfyUI-F5-TTS
- cd custom_nodes/ComfyUI-F5-TTS
- git submodule update –init –recursive
Reload your ComfyUI.
Step 4: Allow ComfyUI to Access your Microphone
This is an issue that some users have had, with Chrome automatically blocking ComfyUI’s usage of the microphone.
- Copy your ComfyUI URL.
2. Visit this chrome page to change your settings
3. Paste it into this box:
4. Change the setting from disabled to enabled
5. Now, when you revisit ComfyUI, reload to update the settings
Step 5: Record your Voice
Press and hold the “Press and Hold to Record” button and read aloud, “This is a test recording to make AI clone my voice.
Step 6: Modify the AI-read text
Change the box below to whatever you want the AI to say with your voice. You can make use of “…” for pauses.
Step 7: Run the workflow
After it’s finished running, enjoy your AI cloned voice under the PreviewAudio node!
Click the triangle to play the audio, and if you want to download it, click the 3 dots and click download
Now you know how to make AI replicate your voice! Isn’t that just sick???
