StepFun Launches StepAudio 2.5 Realtime Voice Model with Roleplay Support
StepFun released StepAudio 2.5 Realtime voice model featuring fully customizable personas. The model grasps paralinguistics (intonation, emotions), supports Chi
◐ Listen to article
StepFun released StepAudio 2.5 Realtime voice model featuring fully customizable personas. The model grasps paralinguistics (intonation, emotions), supports Chinese and English, and connects via WebSocket. It ranked first across all metrics in April benchmarks.