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 personas in Chinese and English. StepFun claims first place across all...
Tag : Voice
Inaudible Audio Attacks Can Hijack AI Voice Models, Study Finds
In brief Researchers at Zhejiang University developed AudioHijack, which hides imperceptible commands in audio to manipulate large audio-language models with a 79–96% success rate. The...
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. The move could help her challenge AI-generated fakes and unauthorized impersonations....