StepFun's StepAudio 2.5 Realtime swept all five voice AI benchmarks, outperforming GPT Realtime 1.5 and Gemini Live with paralinguistic comprehension.

StepFun, the Shanghai lab that builds LLMs that punch above their weight, just turned that same energy on voice.

StepFun's StepAudio 2.5 Realtime swept all five voice AI benchmarks, outperforming GPT Realtime 1.5 and Gemini Live with paralinguistic comprehension.