same thing with pitch/tone/emotion, I'm refering to using SSML or other markup in text to make changes within for example:

Sometimes some words need to be said <prosody volume=”loud>louder</prosody>

I already told you we're <emphasis level="strong">nearly</emphasis> there

For pronunciation I am referring to its use in SSML, for examples:

<say-as interpret-as="number_digit">123456789</say-as>

<phoneme alphabet="ipa" ph="tə.ˈmeɪ.toʊ"> tomato </phoneme>

Thank you for the suggestion!

Currently, pitch/tone and emotion options are available. You can find them in the settings on the left-hand menu.

Regarding pronunciation, may I ask which tool you have in mind that allows users to change pronunciation? We would love to explore it.