Voice Clone Text to Speech

Text to speech, in your voice

Most text to speech reads in a stock voice. This one reads in yours, from 10 to 30 seconds of it.

These are the steps.

Long text

It reads a sentence or two at a time and joins them with a short pause, so a long script comes out as one file. With the Studio model, it speaks about as fast as you'd read it.

Expressions

Pick the Turbo model, and the menu beside the text box adds expressions where your cursor is, in English.

• Laugh and chuckle – for the line that's meant to be funny.
• Sigh and gasp – for a reaction.
• Whisper – for an aside.
• Happy and surprised – for the tone of a sentence.

Languages

With Studio Max or Studio, it reads English, Chinese, German, Italian, Portuguese, Spanish, Japanese, Korean, French and Russian. Leave the language menu on Match my text and it follows what you type.

Use it the right way

Cloning a voice is legal, but some uses of a clone aren't. Stay clear of these.

• Cloning someone without permission – a voice is part of who they are, and some laws forbid it, like Tennessee's ELVIS Act.
• Putting words in a real person's mouth – never make someone seem to say what they didn't.
• Publishing it without saying it's AI – tell your listeners.