Is there a way for the Google TTS service to return the normalised text along with the generated speech file? For example, if “This is 1993” is sent to the service, can it return the verbalised for “This is nineteen ninety three”?
Yes, you can verbalize the year like ordinal numbers or cardinal numbers. You can see this example:
I can speak in cardinals. Your number is 10.
Or I can speak in ordinals. You are 10 in line.
Here is the official documentation about how Text-to-Speech synthesizes the text: