{"id":"step-audio-r1-1-realtime","nom":"Step-Audio R1.1 (Realtime)","editeur":"StepFun","pays":"Chine","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://huggingface.co/stepfun-ai/Step-Audio-R1.1","essayer":"https://www.stepfun.com/studio/audio"},"fiche_auto":false,"page":"https://quelleia.com/voix/modeles/step-audio-r1-1-realtime/","releve":"2026-11-09","en_bref":"8e sur 38 en raisonnement à l'écoute (Big Bench Audio) ; 27e sur 34 au délai avant le premier son.","presentation":"Modèle de dialogue parlé de StepFun qui raisonne pendant qu'il parle, grâce à une architecture séparant la formulation du raisonnement et l'articulation de la parole. Son raisonnement s'appuie directement sur les représentations acoustiques plutôt que sur une transcription.","langues":{"annoncees":null,"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["presentation"],"lu":"https://huggingface.co/stepfun-ai/Step-Audio-R1.1/raw/main/README.md (« Step-Audio R1.1 (Realtime) is a major upgrade to Step-Audio-R1, designed for interactive spoken dialogue with both **real-time responsiveness** and **strong reasoning capability**. »), 23/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/stepfun-ai/Step-Audio-R1.1/raw/main/README.md (« the Realtime variant adopts a **Dual-Brain Architecture**: - A **Formulation Brain** responsible for high-level reasoning - An **Articulation Brain** dedicated to speech generation »), 23/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/stepfun-ai/Step-Audio-R1.1/raw/main/README.md (« Step-Audio R1.1 grounds its reasoning directly in acoustic representations rather than text alone. »), 23/10/2026"}],"classements":[{"id":"voix-a-voix/raisonnement","nom":"Raisonnement à l'écoute, Big Bench Audio","rang":8,"sur":38,"valeur":97.6,"unite":"%","chiffres":{"cout_par_heure_audio_entree":0,"hebergeur":"StepFun"},"voisins":["google-gemini-3-8-live-extended-thinking","spacexai-grok-voice-2-0"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/speech-to-speech","releve":"2026-11-09"}},{"id":"voix-a-voix/delai","nom":"Délai avant le premier son","rang":27,"sur":34,"valeur":1.529,"unite":"s","chiffres":{"cout_par_heure_audio_entree":0,"hebergeur":"StepFun"},"voisins":["openai-gpt-4o-realtime","alibaba-qwen-audio-3-0-realtime-plus"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/speech-to-speech","releve":"2026-11-09"}}],"noms_dans_les_sources":{"aa_voix_a_voix":"Step-Audio R1.1 (Realtime)"}}