StepFun launches StepAudio 3: five audio models, #1 in realtime speech evals
StepFun_ai · x · 2026-09-16
StepFun has released StepAudio 3, a family of five audio models covering realtime voice, speech recognition, speech generation, audio scene generation, and music.
- Designed for voice agents that handle interruptions, reason while speaking, and call tools
- Ranks #1 on Artificial Analysis for Conversational Dynamics (98.9%) and Speech Reasoning (99.7%)
- ASR hits 1.7% WER, matching the best result on the leaderboard
- Available now on the StepFun platform
Related event: StepFun Releases Five StepAudio 3 Models Covering Full Audio AI Stack(6 posts)→
More from Multimodal
- Audio8-TTS-Realistic-Air, a zero-shot voice-cloning TTS model, trends on Hugging Face — Edge0 · 2026-11-02
- Mistral explains why its model-built solver is a first step toward new drugs and batteries — MistralAI · 2026-11-02
- Mistral Large 4 writes a quantum chemistry SCF solver from scratch with one short prompt — MistralAI · 2026-11-02
- Gorgeous dithered pixel art collage serves up a 'great morning' — philipvollet · 2026-11-02
- Clown Prophecy moves to new repo, now uses first clip as reference to fix H3 quality drift — reeight · 2026-11-02
- A 25-year design veteran asks: who still mixes pro software with AI tools? — Opening-Knee-5913 · 2026-11-02