StepFun's Voice AI Topped Every Benchmark. It Also Hears Your Sighs

In brief StepAudio 2.5 Realtime is an end-to-end real-time speech model with fully customizable […]

Inaudible Audio Attacks Can Hijack AI Voice Models, Study Finds

In brief Researchers at Zhejiang University developed AudioHijack, which hides imperceptible commands in audio […]

Taylor Swift Seeks Trademarks for Her Voice and Image to Fight AI Fakes

In brief Taylor Swift files three trademark applications tied to her voice and likeness. […]