# How to use ElevenLabs: a beginner tutorial for AI voiceovers

> ElevenLabs is an AI voice platform that reads your text aloud in a natural-sounding voice. In a browser you paste a script, pick a voice and download the audio. The same account clones a voice, changes the voice on a recording, makes music and sound effects, and transcribes speech. The free plan gives about 10 minutes of speech a month.

Mindket editors · Published 2026-11-06 · Updated 2026-11-06 · https://mindket.com/learn/tools/elevenlabs

## In short

- Open Text to Speech, paste a script, pick a voice and press Generate speech.
- The free plan lists no commercial license. Starter and the plans above it include one.
- A professional voice clone accepts only your own voice.
- Eleven v4 reads tags in square brackets, such as [laughs], as directions for a line.

## What ElevenLabs is

ElevenLabs is a voice AI company, and its website is where most people meet it. You paste text, pick a voice and it reads the text aloud in a human-sounding voice. The same account clones a voice, changes the voice on a recording, transcribes speech with a tool called Scribe, makes music and sound effects, and builds voice agents that talk to callers.

It runs in the browser, with an API for developers, and not on your own computer. The free plan gives 10,000 credits a month, about 10 minutes of text to speech, and lists no commercial license. Starter and the paid plans above it add one.

## What ElevenLabs is good for

- **Narration for videos and courses**: paste a script, choose a voice and download an audio file for a YouTube video, a slide course or a product demo.
- **Audiobooks and long text**: ElevenLabs Studio handles long-form narration, and one generation takes up to 10,000 characters with Eleven v4 and 5,000 with the other models.
- **A copy of your own voice**: an Instant Voice Clone needs about a minute or two of clean audio, so a new script sounds like you without a new recording.
- **A new voice on a recording**: Voice Changer replaces the voice on audio you already made, in pieces of up to 5 minutes.
- **Dubbing a video**: the dubbing tool translates what a video says and voices it in another language.
- **Songs and sound effects**: ElevenLabs Music makes songs and instrumentals from a prompt, and the sound effects tool makes clips of up to 30 seconds.
- **Transcripts**: Scribe writes down what was said in a recording.

## When to use ElevenLabs, and when to pick another tool

| Your job | Use ElevenLabs? | Or try |
| --- | --- | --- |
| Narrate a video you will monetize | Yes, on Starter or above, the first plan with a commercial license | Gemini, whose text to speech has a free tier |
| Write down a private recording | Only if sending the audio to a cloud service is fine | Whisper, which runs on your own computer |
| Turn your documents into a spoken summary | No, it reads the text exactly as you paste it | NotebookLM, whose Audio Overviews read your files back as a summary |
| Make a full song with sung lyrics | It has a music tool, with limits by plan | Suno |
| Clone a voice that is not yours | No. Professional clones accept only your own voice | Hire the speaker and get their consent in writing |

## How to use ElevenLabs, step by step

The menu names are from ElevenLabs' own text to speech guide. They move between releases, so keep a tutorial open beside it.

1. **Create an account.** Sign up at [elevenlabs.io](https://elevenlabs.io). The free plan comes with 10,000 credits a month, about 10 minutes of text to speech.
2. **Open Text to Speech.** Select **Text to Speech** in the sidebar and paste your script into the input box.
3. **Choose a voice.** Pick one from your **Voices** at the bottom left.
4. **Choose a model.** Use the model selector. Eleven v4 is the newest and lists more than 90 languages, and Flash v2.5 lists 32.
5. **Direct the delivery.** With Eleven v4, a tag in square brackets such as [laughs] tells the voice how to read a line. The sliders for stability and speed change how even and how fast it sounds.
6. **Generate and download.** Select **Generate speech**, listen, then press the download button at the bottom right. Every generation spends credits, but regenerating the same text with the same voice and model is free twice within two hours, as long as you have not refreshed the page.
7. **Try a voice clone, if you want one.** An Instant Voice Clone, on Starter and above, needs about 1 to 2 minutes of clean audio and your confirmation that you have the right to clone the voice.

1. Select **Text to Speech** in the sidebar.
   ![An illustration of ElevenLabs with a gold ring around Text to Speech in the sidebar.](https://mindket.com/blog/screens/elevenlabs-1-text-to-speech.webp?v=3519e7dcc82c)
2. Paste your script into the text box. A tag in square brackets such as [laughs] tells an Eleven v4 voice how to read a line.
   ![An illustration of ElevenLabs with a short script pasted in the text box and a gold ring around it.](https://mindket.com/blog/screens/elevenlabs-2-script-box.webp?v=9d935adae1ca)
3. Pick a voice from **Voices** at the bottom left.
   ![An illustration of ElevenLabs with a gold ring around the Voices picker at the bottom left.](https://mindket.com/blog/screens/elevenlabs-3-voices.webp?v=da06b347e911)
4. Open the model menu and choose **Eleven v4**, the newest, or **Flash v2.5**.
   ![An illustration of ElevenLabs' open model menu, listing Eleven v4 and Flash v2.5, inside a gold ring.](https://mindket.com/blog/screens/elevenlabs-4-model.webp?v=4e8efac9d8e1)
5. Select **Generate speech**, listen, then download the take you like.
   ![An illustration of ElevenLabs with a gold ring around the Generate speech button.](https://mindket.com/blog/screens/elevenlabs-5-generate-speech.webp?v=f3cd50288375)

*AI-made illustrations of ElevenLabs's screens, drawn on 6 November 2026 to match these steps. They are not screenshots, so the real app may look different: follow what you see.*

> The tutorials at the top of this page show these steps on screen.

## An example to try

Paste this into the Text to Speech box with Eleven v4 selected. Generate it as written, then again with the tag removed, and compare the two.

````text
Hi, and welcome to the Saturday market. [laughs] Today we have fresh strawberries and the first peaches of the year. Come early, because they sell out by noon.
````

- Does the laugh land where the tag sits, and does the next sentence carry on at an even pace?
- Are the words said the way you would say them? Names and numbers are where a voice slips first.
- Punctuation shapes the pauses, as the Skills Factory tutorial shows, so change a comma to a full stop and listen again.

## Tips for better results

- Paste your own script, with your product names and numbers, and judge the voice on those words. A demo reel proves nothing about your text.
- For a long script, use ElevenLabs Studio instead of one big paste. Kevin Stratvert's tutorial shows it for long-form narration.
- Take WAV from the history tab when you will edit the audio in a video app, and MP3 when you only need to share it.
- Keep clones to your own voice, or one you hold written permission for.

## Plans, licenses and consent

The plan decides what you may do with the audio. A song made on the free plan is for personal use only, and Starter's music license excludes streaming, which Creator and Pro allow. Sound effects split the same way: non-commercial on the free plan and royalty-free in commercial projects on paid plans. A minute of music costs about 900 credits, so the free allowance goes quickly.

Cloning has a consent step. An Instant Voice Clone needs Starter or above. A Professional Voice Clone needs Creator or above, at least 30 minutes of audio and your own voice only, even when someone else agrees, and you read verification lines aloud to prove it.

The tool runs in the cloud, so your text and audio go to ElevenLabs. Keep a recording you cannot share on your own computer.

## YouTube tutorials

- [How to Use ElevenLabs AI (Complete Voiceover Beginner Tutorial)](https://www.youtube.com/watch?v=yDTbAxJ3sKI) (Kevin Stratvert)
- [Create Realistic Text to Speech in 111 Seconds with AI](https://www.youtube.com/watch?v=HSJLQFzgNYo) (ElevenLabs)
- [How to Use ElevenLabs v4: Complete Beginner's Guide [ +Voice Cloning ]](https://www.youtube.com/watch?v=RjLRfnTVlqE) (Skills Factory)
- [How to Create Audiobooks with ElevenLabs for Free (Full Guide)](https://www.youtube.com/watch?v=KI7fb8_XCd0) (ElevenLabs)

## Learn more about ElevenLabs

- [Best AI voice generator in 2026: text to speech, transcription, cloning and live voice compared](https://mindket.com/learn/ai-tools/best-ai-voice-generator)
- [Best AI music generator in 2026: songs, music beds, sound effects and audio cleanup compared](https://mindket.com/learn/ai-tools/best-ai-music-generator)

## Frequently asked questions

### Is ElevenLabs free?

Yes, with a monthly allowance. The free plan gives 10,000 credits a month, about 10 minutes of text to speech, and lists no commercial license. A monetized channel needs Starter or above.

### Can I use ElevenLabs voices on YouTube and earn money?

Yes, on a plan that lists a commercial license. Starter and the plans above it include one, and the free plan does not, so check the plan you made the audio on.

### Can ElevenLabs clone my voice?

Yes. An Instant Voice Clone needs Starter or above and about 1 to 2 minutes of clean audio. A Professional Voice Clone needs Creator or above and at least 30 minutes, and it accepts only your own voice.

### How many languages does ElevenLabs support?

Its newest model, Eleven v4, lists more than 90 languages, and Flash v2.5 lists 32. Voice Changer works in 29 languages with its multilingual model.

### What is a free alternative to ElevenLabs?

For reading text aloud, Gemini's text to speech on Google's free tier, or Kokoro, a free model you run yourself with 54 preset voices. The [voice lesson](https://mindket.com/learn/ai-tools/best-ai-voice-generator) compares them with their limits.

### Can ElevenLabs make music?

Yes. ElevenLabs Music makes songs and instrumentals from a prompt, and a separate tool makes sound effects of up to 30 seconds. The free plan covers personal use only, and the [music lesson](https://mindket.com/learn/ai-tools/best-ai-music-generator) shows what each plan lets you publish.

### Is ElevenLabs safe for private recordings?

Not if the recording must stay on your machine. It runs in the cloud, so your text and audio go to ElevenLabs. Whisper runs on your own computer and suits private audio.

## Sources

- [ElevenLabs: Pricing](https://elevenlabs.io/pricing) (read 2026-11-06)
- [ElevenLabs: Models](https://elevenlabs.io/docs/overview/models) (read 2026-11-06)
- [ElevenLabs: Text to Speech guide](https://elevenlabs.io/docs/product-guides/playground/text-to-speech) (read 2026-11-06)
- [ElevenLabs: Instant Voice Cloning](https://elevenlabs.io/docs/product-guides/voices/voice-cloning/instant-voice-cloning) (read 2026-11-06)
- [ElevenLabs: Professional Voice Cloning](https://elevenlabs.io/docs/product-guides/voices/voice-cloning/professional-voice-cloning) (read 2026-11-06)
- [ElevenLabs: Voice changer](https://elevenlabs.io/docs/overview/capabilities/voice-changer) (read 2026-11-06)
- [ElevenLabs: Introducing Eleven v4](https://elevenlabs.io/blog/eleven-v4) (read 2026-11-06)
- [ElevenLabs: Eleven Music](https://elevenlabs.io/music) (read 2026-11-06)
- [ElevenLabs: Sound effects](https://elevenlabs.io/sound-effects) (read 2026-11-06)
- [Kevin Stratvert on YouTube: How to Use ElevenLabs AI](https://www.youtube.com/watch?v=yDTbAxJ3sKI) (read 2026-11-06)
- [ElevenLabs on YouTube: Create Realistic Text to Speech in 111 Seconds](https://www.youtube.com/watch?v=HSJLQFzgNYo) (read 2026-11-06)
- [Skills Factory on YouTube: How to Use ElevenLabs v4](https://www.youtube.com/watch?v=RjLRfnTVlqE) (read 2026-11-06)
- [ElevenLabs on YouTube: How to Create Audiobooks with ElevenLabs for Free](https://www.youtube.com/watch?v=KI7fb8_XCd0) (read 2026-11-06)

[Start the lesson](https://mindket.com/learn/ai-tools/best-ai-voice-generator)