Repack preset voices: renamed, tagged, previews now model-synthesized

Trim README prose (#5)

Add OmniVoice to benchmark tables; new headline; clearer WHO wording (#4)

Add banner, marketing intro, restructured result tables (normalized headline + both WER tables) (#3)

Link ZeroBench-TTS via datasets + model-index, refresh benchmark results (#1)

Publish ZeroTTS v1