Tutorial 16aGoing further

AI voice-over

Turn text into speech in LUVI: pick a voice-over model and a voice, set the stability and language, and generate.

00:00 / 01:24

What this video covers

There are three things you can do with sound in LUVI: turn text into speech, make music, and transcribe a recording. This part covers voice-over.

Audio is a type of model in the workspace. Press Choose Model and open the Audio tab.

Video models that make their own sound are listed here too, and the audio models come last. The quickest way is to search for the model by name.

Several models do voice-over: ElevenLabs, Gemini, MiniMax Speech and xAI. We're choosing ElevenLabs v3.

For voice-over, the prompt box holds the script itself: whatever you type is read out word for word.

The Voice menu lists ready-made voices. The icon shows whether a voice is female or male, and the brackets show its accent.

A low Stability gives a more expressive read; a high one keeps it steady and even.

In the Language box, type a language code — EN for English.

The price depends on how long the text is, and the estimate updates as you type. Let's press Generate.

A few seconds later, the voice-over is ready. Press play to hear it.

The voice-over is saved to your library as an audio file. In the next part, we'll make music.

Try it yourself

Create a free LUVI account and follow along with the video.

Get started

More from Going further

All tutorials