What’s new: natural pauses and prosody control in TwelveLabs
You asked for more control. We built it. Natural pauses and prosody tuning are now live for cleaner, more human-sounding audio.
Ethan Park
TwelveLabs
If you have ever heard a voiceover that feels just a beat too fast, you already know why this update matters. Natural pauses are not a luxury. They are the difference between a voice that lands and one that rushes.
What changed
We shipped two improvements: pause control and prosody tuning. Pause control lets you shape timing at sentence boundaries. Prosody tuning helps you dial emotion without breaking clarity.
If you only try one thing, add a short pause after a key claim. It is a tiny change that makes the message stick.
Why it matters
These changes are about trust. When a voice sounds natural, people listen longer. In our internal tests, teams reported fewer rewrites and less time spent on manual editing.
How to use it
Start with your script and identify the moments where you want the listener to breathe. Add a pause tag or break the line. Then adjust prosody for emphasis. Think of it like direction, not settings.
Here is a simple example:
const payload = {
text: "This is the moment. Take a breath. Then hit play.",
pauseBehavior: "natural",
prosody: { emphasis: "moderate" },
};The bigger picture
We are building toward voices that keep your intent intact at scale. That means more control for creators and more consistency for teams that ship audio weekly.
Try it in TwelveLabs Text to Speech and tell us what you hear.
Related posts

How we cut dubbing turnaround by 60% with a smarter review loop
A guide to faster dubbing without sacrificing quality, built on a review loop that respects creative intent.

Latency, quality, and control: the engineering tradeoffs behind great AI audio
Behind every great voice is a set of engineering tradeoffs. Here is how we balance latency, quality, and control without cutting corners.

From script to studio: a voiceover pipeline in a day
A practical walkthrough to ship high-quality voiceovers fast, with a workflow that balances speed, control, and creative intent.
