Need a professional voice for your content? With ElevenLabs, you can use AI to generate bespoke voice-over on demand – whether it mirrors your own voice, someone you represent, or a completely fictional character.

In this lesson, we'll cover:

Finding the right voice for your project
- Choosing potential voices from the extensive voice library
- Generating a unique synthetic voice with the voice design tool
- Creating a voice clone of yourself, or someone else (with their permission!)
Using the text-to-speech tool to generate great-sounding voiceover
Keep exploring: other AI voice tools & workflow ideas

- Creating classic audio formats like audiobooks or podcasts
- Adding narration and voiceover to videos, from short-form TikTok formats to longer YouTube videos or tutorials
- Bringing gravitas to marketing assets like demos, decks and showreels
- Offering live audio help, by connecting the voice to a knowledge base, so it can answer customer questions
- Generating character voices for games, stories, apps and interactive experiences
- Create localised dubs of existing content in new languages
- Mockup ‘scratch’ creative work with an AI voiceover ahead of professional recording sessions
Generation at scale: if you have hundreds of articles on your website, you can easily turn them into audio assets at a pace that would be impractical with live voiceover
Convenience: if you market an individual or ‘personality’, you can clone their voice, allowing you to quickly create content that sounds like them, without needing to get them back in front of a microphone
Distinctiveness and consistency: a tool like this offers a more bespoke sound than the default AI voices offered in some social media apps, while deploying the same voice across all your content creates another element of brand feel, along with your palette, tone of voice and so on
Diverse voices to match your audience: whether you want to A/B test different voices in ads, or create different voices for content aimed at different demographics (including in local languages for international campaigns), AI makes it easy

1) Getting started

Let’s head over to ElevenLabs, sign up, and land on the home screen. (The free tier will offer you 10 minutes of synthetic speech to play with, while the $5 starter tier offers more credits and lets you experiment with Voice Cloning, too.)

First, we’ll be adding the voices we want to use to the ‘My Voices’ section. Then, we’ll use the text-to-speech tool to generate audio using those voices.

2) Finding the perfect voice

2a) Choosing a voice from the Library

To explore the library of original voices, click Voices in the left hand navigation, then Library at the top.

Looking for something specific? Use the search bar to seek out adjectives such as ‘smooth’, ‘husky’ or ‘newsreader’, or filter by language, accent and use‑case.

Each voice comes with a demo clip. Once you find a voice you like, click + Add to save it to your Voices for later use.

Tip: speech you generate later will match the source recording quality, so you’ll want to avoid any recordings that have a tinny sound, reverb, or audio artefacts.

2b) Designing a synthetic voice

Want a voice that’s truly unique? Then try out the Voice Design function. You can access this tool from the Home screen, or go to Voices → My voices → Add a new voice, and choose Voice Design.

In this control panel, you can prompt the AI for the exact voice you want – be descriptive!

In the second text box, you can enter the sample dialogue you’d like the candidate outputs to recite.

Clicking ‘generate’ will deliver three possible matches in just a few seconds. If one of them is suitable, click it to save.

Not satisfied? Try adding more detail to your prompt, or simply hitting ‘regenerate’ (a given prompt can generate quite a wide range of voices!)

2c) Cloning a ‘real life’ voice

If you’re using the Starter tier or above, you’ll have access to Instant Voice Cloning, which, just like Voice Design, can also be accessed by Voices → My voices → Add a new voice.

This tool rapidly generates a voice that closely (although not always perfectly!) matches a recording of a speaker.

The tool works with as little as 10 seconds of audio, but more material usually improves accuracy. In our video tutorial, we uploaded eight minutes of audio to get a pretty good impression.

Here’s an example of an original voice vs. a clone:

Tip: The ‘cloned voice’ will match the tone and intonation of the original recording – for example, if you talk in a calm, soft voice, so will the clone. If you hope to create a range of content by the same person with different tonal qualities (e.g: chatty and confessional sometimes, straightforward and explanatory other times) then record a different set of source audio for each mood, then create a different voice for each mood.

Upgrade: If hyper-realism is important – for example, if your intended audience is well aware of what the target voice ‘really’ sounds like – you might want to upgrade to the Professional Tier for access to Professional Voice Cloning. This high-end feature requires at least 30 minutes of audio (although multiple hours are recommended) and takes several hours to generate.

3) Generating speech

Now you’ve successfully added your candidate voices to ‘My Voices’, you can head to the text-to-speech tool in the left-hand navigation.

In this simple interface, we can simply add our script to the central pane, while on the right hand side, we can choose the target voice, as well as play around with a few settings. Hit Generate speech and the audio will start playing in just a few seconds!

Increasing similarity and style exaggeration often nudges the output closer to your target tone. At default settings, voices can sound slightly ‘well‑spoken’ or narrator‑like.

Prefer an earlier version to your current experiment? Use the ‘history’ view, in the right-hand-panel, to find your previous generations.

Tip: each generation uses up credits depending on the amount of text entered. So, while you’re testing voices, it’s best to use just a few sentences to experiment with. When you’re happy with the sound, you can add your full script for generation, all in one go.

And we’re done! You can now generate polished, professional AI voice‑overs at will – enjoy experimenting.

Keep exploring…

ElevenLabs also offer a host of other voice-related features to try out:

Voice changer: converst existing recordings to a new voice
Dubbing: replaces source speech with similar-sounding vocal in a different language
Studio: builds longer spoken word pieces based around articles or books
Sound effects: generates sound effects rather than speech
Speech to text: turns audio recordings into annotated transcripts
Conversational AI: deploy talking agents that can offer advice based on your content (Look in the bottom-right hand corner of this page and choose ‘Start a call’ to try out talking to me!)

You could also consider using AI in other parts of your workflow:

Working with LLMs like ChatGPT, Claude or Gemini to generate the dialogue
Using the generated speech to animate avatars in lipsync tools like Hedra
Creating AI-driven video to accompany the narration using Kling
Adding backing music generated with an AI tool like Suno
Using ElevenLabs API to generate speech ‘on demand’ in an app

Create a custom voice for your brand using ElevenLabs