Post-Cutoff.com
  1. Home
  2. Models
  3. StepAudio 3 Realtime

StepAudio 3 Realtime

StepFunpreviewaudio/speechStepAudio 3

Chinese and English. Preview ids will be retired for a paid GA version when the trial ends. Predecessor stepaudio-2.5-realtime (2026-05-26; persona role-play, project page https://stepaudiollm.github.io/step-audio-2.5-realtime/ with self-reported 86.36 general dialogue / 79.80 spoken QA / 82.18 paralinguistics, claimed to beat GPT-Realtime-1.5 on StepFun's evals). Technical report arXiv 2609.14005 (56.0% task success on tau-Voice).

Input
audio, text
Output
audio, text
License
proprietary
Pricing
input: $0 · output: $0 (free during limited-time preview (successor stepaudio-2.5-realtime: $1.50 in / $0.30 cached / $10.00 out per 1M tokens)) source
Verified
2026-09-29

How to call it

ProviderModel idEndpoint / URLDocs
StepFun API (Realtime WebSocket)stepaudio-3-realtime-preview—docs
StepFun API (Chat Completions)stepaudio-3-chat-preview—docs

Notable capabilities (2)

StepFun's full-duplex voice agent model; part of the five-model StepAudio 3 family (Realtime, ASR Max, TTS, Gen, Music).

Sources: https://platform.stepfun.ai/docs/en/guides/models/audio · https://platform.stepfun.ai/docs/en/pricing/details · https://arxiv.org/abs/2609.14005

Timeline entry

  1. StepFun releases StepAudio 3 family; its Realtime model tops Artificial Analysis full-duplex rankings ★★★

    Chinese lab StepFun launched StepAudio 3, five audio models (Realtime, ASR Max, TTS, Gen, Music). StepAudio 3 Realtime, a "think-while-speaking" full-duplex voice model, ranked #1 on Artificial Analysis for Conversational Dynamics (98.9%) and Speech Reasoning (99.7%), and StepAudio 3 ASR ranked #1…

Other StepFun models

StepAudio 3 ASR Max / StepAudio 3 TTS · StepFun Step-Audio-EditX · Step 5 Preview