Comment by drewbitt
8 months ago
At least 5 brand new accounts are commenting on this post, sometimes multiple times across Inworld submissions here.
You say SOTA but I don't see any benchmarks/leaderboards that back this up except in voice cloning, which I don't particularly care about. Consider getting it added to https://huggingface.co/spaces/TTS-AGI/TTS-Arena-V2 and https://artificialanalysis.ai/text-to-speech/arena.
We'll put the models there as soon as we can, yes.