Is there a way to return a string instead of an audio?

[martino-vic]

I'm searching for a way to phonetically transcribe Australian English, or g2p. Saw that gTTS gives the option to pick Australian English but can't see a way how to get the output as a string rather than a sound wave.

Any help or hints appreciated

[martino-vic]

Trying to plug in the gTTS output into allosaurus right now, a package that converts sound waves to ipa