{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/stepaudio-3-realtime/","md":"https://postcutoff.com/m/stepaudio-3-realtime/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"stepaudio-3-realtime","name":"StepAudio 3 Realtime","org":"StepFun","family":"StepAudio 3","released":"2026-09-15","status":"preview","type":"audio/speech","modality_in":["audio","text"],"modality_out":["audio","text"],"open_weights":false,"model_license":"proprietary","context_window":null,"max_output":null,"knowledge_cutoff":null,"pricing":{"input":0,"output":0,"unit":"free during limited-time preview (successor stepaudio-2.5-realtime: $1.50 in / $0.30 cached / $10.00 out per 1M tokens)","source":"https://platform.stepfun.ai/docs/en/pricing/details"},"price_line":"Free","access":[{"provider":"StepFun API (Realtime WebSocket)","model_id":"stepaudio-3-realtime-preview","docs":"https://platform.stepfun.ai/docs/en/guides/models/stepaudio-3-realtime"},{"provider":"StepFun API (Chat Completions)","model_id":"stepaudio-3-chat-preview","docs":"https://platform.stepfun.ai/docs/en/guides/models/stepaudio-3-realtime"}],"capabilities":[{"name":"Think-while-speaking full duplex","detail":"Runs private chain-of-thought in parallel with spoken output; distinguishes real interruptions from backchannels; asynchronous tool execution (web search, knowledge retrieval).","first":false,"discovered":"launch","source":"https://arxiv.org/abs/2609.14005"},{"name":"#1 on Artificial Analysis conversational dynamics","detail":"98.9 on Artificial Analysis Full-Duplex Bench (Conversational Dynamics) and 99.7% Speech Reasoning at launch, ahead of Qwen Audio 3.0 Realtime Plus and GPT-Live-1 per StepFun.","first":false,"discovered":"launch","source":"https://x.com/StepFun_ai/status/2099916376274313630"}],"entry":"2026-09-15-stepfun-stepaudio-3","notes":"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).","verified":"2026-09-29","body_md":"StepFun's full-duplex voice agent model; part of the five-model StepAudio 3 family (Realtime, ASR Max, TTS, Gen, Music).\n\nSources: https://platform.stepfun.ai/docs/en/guides/models/audio · https://platform.stepfun.ai/docs/en/pricing/details · https://arxiv.org/abs/2609.14005","page_url":"https://postcutoff.com/m/stepaudio-3-realtime/","standing":{"kind":"speech and audio","newer_count":25,"newer":[{"id":"nemotron-3-5-transcribe","name":"NVIDIA Nemotron 3.5 Transcribe (30B-A4B)","org":"NVIDIA","released":"2026-10-28","page_url":"https://postcutoff.com/m/nemotron-3-5-transcribe/"},{"id":"hy-simulmt-30b-a3b","name":"Hy-SimulMT-30B-A3B","org":"Tencent","released":"2026-10-22","page_url":"https://postcutoff.com/m/hy-simulmt-30b-a3b/"},{"id":"eleven-realtime-v1-max","name":"Eleven Realtime v1 Max / Mini","org":"ElevenLabs","released":"2026-10-20","page_url":"https://postcutoff.com/m/eleven-realtime-v1-max/"},{"id":"voxtral-mini-transcribe-3","name":"Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-mini-transcribe-3/"},{"id":"voxtral-small-transcribe-3","name":"Voxtral Small Transcribe 3","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-small-transcribe-3/"}],"before":{"id":"step-audio-editx","name":"StepFun Step-Audio-EditX","org":"StepFun","released":"2025-11-06","page_url":"https://postcutoff.com/m/step-audio-editx/"},"after":null,"weights":"closed","licence":"proprietary","licence_permissive":false,"summary":"Closed weights; access is hosted only."}}