How much time it takes to convert text to speech in speech synthesis

I'm trying to play post audio such as this.

The problem is, when I click the play button. It just plays after some seconds. It's usually around 5-6 seconds. I'm afraid that the user will get blind and say what the heck is going on?

How do I calculate how much time it takes to convert text to speech in speech synthesis, I can show preparing to play.

Note: This domain belong to me. and it's not an ad.