Hacker News Reader

Sounds slow and like something from an anine

Speech speed is always a tunable parameter and not something intrinsic to the model.

The comparison to make is expressiveness and correct intonation for long sentences vs something like espeak. It actually sounds amazing for the size. The closest thing is probably KokoroTTS at 82M params and ~300MB.

I think he meant overacting typical for English dubs.

The voices sound artificial and a bit grating. The male voices especially are lacking, especially in depth: only the ultimate voice has any depth at all, while the others sound like teenagers who haven't finished puberty. None of the voices sound quite human, but they're all very annoying, and part of that is that they sound like they're acting.

I heard a little DVa from Overwatch.

The only real questions are which Chinese gacha game they ripped data from and whether they used Claude Code or Gemini CLI for Python code. I bet one can get a formant match from output this much overfit to whatever data. This isn't going to stay up for long.

Reply on news.ycombinator.com