Speech synthesis UI redesign

We're excited to share that an all new speech synthesis experience launched today. Here are some details we wanted to highlight:

Streamlined experience
Instead of immediately being greeted by all the controls, you are now shown settings as you start typing or pasting in content, you can easily pick voices without them interrupting your experience, and advanced settings are tucked away in a new sidebar so they're there when you need them. That said, should you want to tweak those results and quickly generate back and forth you can also directly do that from the new sidebar.

History easily accessible in a new tab
History no longer takes up a whole chunk of your screen and instead has its own dedicated tab where you can easily browse your old generations. We've made it easy to copy old prompts too when you hover over them or you can just play or download anything you might need.

Visual design lift
You'll notice the page is a lot more expressive too - featuring our new brand's sound wave in the background that blurs away as you start typing so that your focus is on the content, this is just the beginning of many of the new brand elements making their way into the product.

A whole new set of components
Part of what this work also gets us is a whole new set of frontend components rethought from the ground up like tabbed headers, icon buttons, new tooltips, a new side panel, and a few other things—this will make future frontend work a lot faster too as we've thought through the different states and components we might need and their application beyond the speech page.

Up next
We know some people have much deeper workflows with Speech Synthesis where they can be editing entire scripts, while we offer Studio as our editor for long-form projects, we'll shortly be following up with an immersive view on the speech synthesis page as well, turning your layout into a dedicated workspace with every setting you need easily accessible, a layout perfectly tailored towards our power-users.

TEXT TO SPEECH

Create human-like voices with our Text to Speech (TTS) system, built for high-quality narration, gaming, video, and accessibility. Expressive voices, multilingual support, and API integration make it easy to scale from personal projects to enterprise workflows.