[Shorts Studio] #11 How To Clone Your Voice With ElevenLabs

If you’re creating faceless Shorts, or just want to save time recording your own voice, then voiceover becomes the backbone of your content.

And ElevenLabs is the most natural-sounding AI voice tool available right now.

In this lesson, you’ll learn:

• How to generate voiceovers using 3 different methods

• What makes an AI voiceover actually sound good

• And how to use it in your Shorts workflow

Let’s start with the basics.

What Is ElevenLabs?

ElevenLabs is an AI tool that turns written text into human-like voiceovers.

You give it a script. It reads it aloud.

But unlike most text-to-speech tools, it doesn’t sound robotic. It can sound relaxed, excited, thoughtful—even sarcastic. The difference is in the tone, pacing, and emotion.

And when used well, the output feels like a real human.

Why Use A Voiceover?

A good voiceover can:

• Make your short feel more premium

• Deliver tone (which text on screen alone can’t do)

• Free you from needing to be on mic or camera

And you don’t have to hire a voice actor, rent a mic, or spend hours editing audio.

But ultimately a good “voice” keeps your viewer engaged.

@askvinhIf you lose people when you talk, it's because you're not engaging enough. The 3 areas you need to think about to be engaging are: 1. Auditory engagement - how you sound 2. Visual engagement - how you use body language and hand gestures 3. Content - is what you're saying interesting to the person? Practice improving these 3 areas if you want to keep people engaged when you speak. It's that simple! Do YOU struggle with keeping people engaged?

Tiktok failed to load.

Enable 3rd party cookies or use another browser

Who Is ElevenLabs Best For?

You’ll get the most value out of ElevenLabs if:

• You’re making faceless content

• You want to sound more polished without recording yourself

• You want to create a “voice” for your channel that’s consistent across videos

• You want to create videos in different languages

• You want to move faster without sacrificing quality

If you're already writing scripts, ElevenLabs makes it easy to scale.

3 Ways To Create Voiceovers With ElevenLabs

There are three ways to generate a voiceover using ElevenLabs.

Way #1: Use A Voice From The Library

This is the fastest path.

ElevenLabs has a Voice Library with thousands of community-made voices. Many are clones or custom creations, and you can preview before using.

Some of the most popular, default voices include:

• Rachelle—neutral American female, often used for explainer content

• Mark—male voice, good for conversational writing

• Dakota H—female, clean, natural

There are hundreds of voices to choose from.

I recommend spending 15 minutes browsing the voice library. Filter on your preferences. Pick one that fits the tone of your video or just a voice that sounds good to you.

You can always switch voices later.

Pro tip: search using a sample of your voice to match your style and tone.

Way #2: Design Your Voice With An AI Prompt

If you want something specific, you can use the Voice Design tool.

You describe the voice in plain language, and ElevenLabs generates a few options.

Example prompt:

“Young American female. Casual tone. Slightly upbeat and friendly, but not over-the-top.”

You can also specify accent, age, emotion, speed, pitch, and more.

Preview a sample, tweak if needed, and save the one you like.

Way #3: Clone Your Own Voice

This is useful if you want your Shorts to sound like you—but you don’t want to record every time.

Here’s how it works:

1. Upload a 1–5 minute sample of your voice (must be clean and clear)

2. ElevenLabs trains a model that mimics your tone, cadence, and speech patterns

3. You can now generate scripts in your own voice

Cloning works best when your sample includes natural speech. Try to record yourself speaking normally.

How To Use Your Voice With ElevenLabs (Text to Speech Tool)

Once you’ve written your script and picked your voice, generating the audio is simple.

Here’s how to do it step by step:

1. Go to the “Text to Speech” tab This is where you generate your audio from a written script.

2. Paste your script into the editor Make sure your text includes punctuation, line breaks, or any emphasis markers you want the voice to pick up on. (See the next section for a few tips.)

3. Choose your voice Select from your custom voice, cloned voice, or one of the voices from the ElevenLabs library. You can preview each voice before generating.

4. Click “Generate” ElevenLabs will read your script and produce a voiceover. This usually takes just a few seconds.

5. Listen—and tweak If something sounds off, edit the script and try again.

That’s it.

You’ll probably do a few rounds of tweaking before it sounds just right.

But once you're happy with it, download the audio file from ElevenLabs and drop it into your video editor (CapCut, Descript, Hedra, Final Cut, etc.)

Done. That’s your voiceover.

What Makes An AI Voiceover Sound Good?

Here’s where most creators mess up.

They think the tool does all the work. So, they write a clean, polished script and expect the AI to deliver it with the timing, tone, and personality of a real person. But that’s not how it works.

A great voiceover is 50% the voice…and 50% the script.

If you want your video to sound like a polished audiobook, fine—ElevenLabs can do that straight out of the box. But if you want it to sound like a real person, you need to intentionally add a little friction..Real people pause. Emphasize the wrong word. Trail off mid-thought. Say the same thing twice, use short sentences, interrupt themselves, and speak with emotion.

There are a few techniques that help:

• Writing how you speak

• Using punctuation to create rhythm and breaks

• Guiding tone through context or dialogue-style cues

• Playing with ALL CAPS to emphasize key moments

• Using AI to “unpolish” your script

We’ll cover each one in a second.

Or, if you want to skip ahead for the prompts: