You can use Delphi to not only scale your mind but also create text-to-speech outputs using your Digital Mind’s voice.

To get started, go to Voice within the Build tab. Within the Voice Playground, you can enter the text that you would like to turn into speech. Select Generate to create the desired speech output. The files can be downloaded.

If you want to make changes to how your voice sounds on Delphi, utilize the Voice Creation Guide.

Adding Pauses

A pause will help break up your voice output. For example, if you are generating ad reads for a podcast segment, a pause can be inserted between separate ads.

The best way to add pauses is by using the syntax <break time="2.0s" />. This will introduce a natural pause into the speech, just as a human would.

Here is an example:

"Welcome to the show!" <break time="1.3s" /> "I am your host, Ben Richardson."

Specify break duration in seconds using <break time="Xs" /> where X can range from 0.1 to 3 seconds. 3 seconds is the max pause time. Some pauses may add natural filler sounds like “uh” during longer pauses, especially if you place break tags at the beginning or end of your text.

Custom Pronunciations

Here’s how you can instruct your Digital Mind to pronounce specific terms, names, or phrases in a specific way.

Within the Voice page, select Pronunciation Table. Add the word that is being mispronounced and phonetically spell how you want the word to be pronounced.

Here is an example:

Word - “Delphi”

Pronunciation - “Delfeye”

This will correct the pronunciation for both text-to-speech voice output and user interactions.