MarkTechPost:StepFun Releases StepAudio 2.5 Realtime: An End-to-End Voice Model with Roleplay-Specific RL…
原文摘要:StepFun, the Shanghai-based AI lab, released StepAudio 2.5 Realtime in May 2026 — an end-to-end real-time speech large language model with fully customizable persona capabilities. 来源:MarkTechPost。建议继续查看原文,重点核对它影响的工具入口、成本、风险和真实使用场景。