Read our guide to see how you can make the audio pronunciation sound just right with

Basic tips

Use the Play button

When you type in your text, you can click the "Play" button and listen to how the audio sounds. This will help you detect if there are any mispronunciations.


Check the spelling

We all make typos, so make sure to double-check your spelling to get the correct pronunciation. Adding the necessary commas, hyphens, and question marks can be the key to making the AI voice sound the way you want it to.


One language at a time

Try not to mix languages on one slide. If you want to use multiple languages, it is better to have a different slide for a different language.

To make it just right…

You can insert a pause

If you need a certain pause in the audio, type in a break tag where you need in. For example, if you need a one-second pause in the text, you would type:
Hello everyone! <break time="1s" /> This is my first video.


Adjust the pronunciation

If you feel like a word is not pronounced correctly, you can put a hyphen in this word to help the AI. For example, writing "lap-top" instead of "laptop".

You can also use the Prosody SSML tag which allows you to change how a specific word or sentence will sound. You can change rate, volume, pitch, contour, and range.


Emphasize words

You can emphasize words by wrapping them into pitch tag with decreased rate and short pause before the word, like this: Entrance is on the ground level. As an option you can change Contour of the word: word


Use phonemes to improve pronunciation

You can use phonetic alphabets to make any word sounds perfect. For this you can use a phoneme SSML tag, like this: <phoneme alphabet="ipa" ph="təˈmeɪtoʊ"> tomato </phoneme>