I think a lot of the remaining gap is due to a lack of high-quality training data -- most of the open-source models are trained on public-domain audiobooks (e.g. LJ Speech).
However, good training data (large amounts of annotated recordings by professional voice actors) is expensive to create, and unlike code, there's not a tradition of people sharing it.
https://github.com/NVIDIA/tacotron2
https://github.com/CorentinJ/Real-Time-Voice-Cloning
https://github.com/mozilla/TTS
I think a lot of the remaining gap is due to a lack of high-quality training data -- most of the open-source models are trained on public-domain audiobooks (e.g. LJ Speech).
However, good training data (large amounts of annotated recordings by professional voice actors) is expensive to create, and unlike code, there's not a tradition of people sharing it.