You mean the voice, or the grammar? The grammar part is outside of the scope of a synthesizer. That's completely up to the user.
Or you want a model which translates normal English into Yoda-English (on text level) and then attach a speech synthesizer on that?
Or I guess an end-to-end speech synthesizer, a big neural network which operates on the whole sentence at once, could also internally learn to do that grammar transformation.
Or you want a model which translates normal English into Yoda-English (on text level) and then attach a speech synthesizer on that?
Or I guess an end-to-end speech synthesizer, a big neural network which operates on the whole sentence at once, could also internally learn to do that grammar transformation.