StepFun Launches StepAudio 3 Family of Five Audio Models

StepFun released StepAudio 3, a family of five audio models spanning realtime voice, ASR, TTS, sound effects and music, with its realtime model topping benchmarks and ASR reaching 1.7% WER, signaling full-stack competition in audio AI.

2026-09-15 ~ 2026-09-16 · 4 related posts

• StepFun drops five StepAudio3 models, claiming three Artificial Analysis world No.1s — 新智元 · 2026-09-15
• StepFun launches StepAudio 3: five audio models, #1 in realtime speech evals — StepFun_ai · 2026-09-16
• StepFun launches StepAudio 3: five audio models topping realtime voice leaderboards — StepFun_ai · 2026-09-16
• StepAudio 3 API docs detail full model lineup from TTS to music generation — StepFun_ai · 2026-09-16