New from Resemble: Scaling TTS with Variables, and Auto Save!

Sep 28, 2020

It seems like not too long ago that I sent out an email outlining new features including real-time heteronym detection, and more download options. I’d love to hear your thoughts and what you’d like to see next. For now, we have a couple of massive new features I think you’ll love.

 

Scale TTS with Your Custom Voice with Variables

Variables enable you to create permutations of speech and drop in dynamic bits. Our beta customers have loved how this has helped them scale custom voice TTS to deliver thousands of dynamic speech assets. Here’s how it works.

Within the editor, type in your sentence. Use the double brackets to type in your variable name and you’ll see the enter to create new variable. You can also transform any word into a variable from the sidebar by highlighting and going to the sidebar.

Now you can go ahead and fill in the variable with their values. Simply double click on the variable and type out your variable values:

Once you’ve filled out the values, you’ll see the list expand into all of the possibly permutations.

Never lose your work with Auto Save

This one is a tremendous quality of life update. As you type into the editor, we automatically save the document so you can come back and edit it later without having to worry about losing your work. The status bar at the bottom of the editor shows you when the document was last saved or when a save is in progress.

That’s all for now. We’ve got another round of exciting updates coming very soon! In the meantime, you can fill out this form to let us know what you’re building with custom voices.

More From This Category

Replay Attacks: The Blind Spot in Audio Deepfake Detection

Replay Attacks: The Blind Spot in Audio Deepfake Detection

We're thrilled to announce that groundbreaking research from our team at Resemble AI and collaborators, detailed in the paper "Replay Attacks Against Audio Deepfake Detection," has been accepted for presentation at the prestigious Interspeech 2025 conference! This...

read more
Voice Design: Transforming Text into Unlimited AI Voices

Voice Design: Transforming Text into Unlimited AI Voices

Today, we're thrilled to unveil Voice Design, our most groundbreaking feature yet. Voice Design represents a fundamental shift in how creators approach voice generation by translating simple text descriptions into fully-realized AI voices in seconds.The Power of...

read more