DailyPapers(@HuggingPapers):Tencent releases AuK, a unified speech generation and editing model It handles zero-shot TTS, instruction-driven content/acoustic/paralinguistic editing, plus enhancement and separation through one natural-language interface. The distilled AuK-Flash version runs 4.5x faster.

DailyPapers

@HuggingPapers

Tweeting interesting papers submitted at Submit your own at and link models/datasets/demos to it!

加入 March 2025

4 正在關注 21.6K 粉絲

DailyPapers@HuggingPapers

2026.09.09 12:15

Tencent releases AuK, a unified speech generation and editing model It handles zero-shot TTS, instruction-driven content/acoustic/paralinguistic editing, plus enhancement and separation through one natural-language interface. The distilled AuK-Flash version runs 4.5x faster.