Studio Updates (August 2022)

We’re constantly working to improve your Studio experience. Here’s a summary of what’s new with Studio.

Improvements

Our August 2022 WellSaid Voice Model update includes major improvements in pronunciation and a new Respellings tool to help with phonetic spelling.

With our new model, we focused on improving the voice avatar’s correctness:

  • more words are pronounced correctly, more often

  • sentence intonation is generally more natural, including questions

  • the AI is smarter with numbers and knows how to say a dollar amount, a year, or a phone number

  • the AI is smarter with specialized text and is better at saying URLs, acronyms, or an abbreviations

Respellings

We have also launched the first iteration of a respelling system that allows you to give precise instructions to the AI. This new system allows you to control word pronunciation and emphasis. Making it easier to tell the AI exactly what sound each syllable should make and which syllables should be emphasized.

Fixes


Fixed: Audio Cut-Off - Customers often experience a feeling of truncation or abrupt ending to the clips they generate in WellSaid Studio. Our latest release resolves this issue.

Accessing previous version

You can keep creating using the previous version by following the steps below:

To enable our previous version: 

1. In Studio, select Account>Settings on the right menu.

2. Toggle TTS Versions to enable.

HubSpot Video

Create audio:

1. Open a new or existing project.

2. Select your chosen voice avatar and its style, and select Previous from the Version drop-down menu.

3. Create content as usual!