Skip to content

Text to speech with AI

Paste the text into the Voiceover section, pick a voice and language and run it. In a few seconds an audio track appears that you can lay over a clip. The ElevenLabs model reads many languages, and pauses and stress come from punctuation and short sentences.

Updated:

Step by step

  1. Paste the text

    Use short sentences. A period gives a pause, and commas and ellipses soften the delivery.

  2. Pick a voice

    Listen to a couple of voices and choose the one that fits the age and mood. You can change the voice without rewriting the text.

  3. Download and layer

    The track downloads as a file. Lay it over the clip in any editor or pair it with lip-sync.

Where it is in ClickBait

Frequently asked questions

Which languages are supported?

The languages of the ElevenLabs model. The list and details are on its page.

Which voices are available?

The list is in the Voiceover section. You can listen to each voice before you run it.

The stress falls on the wrong syllable. What do I do?

Mark the stress or rewrite the word. A short phrase without complicated abbreviations reads more cleanly.

How do I add a pause in a specific place?

Put an ellipsis or a separate paragraph where you want the pause. The model reads punctuation as a cue for breathing.

Can I voice a long text?

Yes, but split it into paragraphs by meaning and voice them in parts. That makes it easy to fix one place without redoing everything.