{"id":"alibaba-qwen-audio-3-0-realtime-plus","nom":"Qwen Audio 3.0 Realtime Plus","editeur":"Alibaba","pays":"Chine","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://www.alibabacloud.com/help/en/model-studio/newly-released-models"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/alibaba-qwen-audio-3-0-realtime-plus/","releve":"2026-11-09","en_bref":"2e sur 12 à l'indice voix à voix d'Artificial Analysis ; 2e sur 38 en raisonnement à l'écoute (Big Bench Audio) ; 2e sur 31 en tenue de la conversation (Full Duplex Bench) ; 28e sur 34 au délai avant le premier son.","presentation":"Modèle de dialogue vocal en duplex d'Alibaba, édition standard, servi par l'API Model Studio. Il cherche l'équilibre entre l'intelligence du modèle et le rythme naturel de la conversation.","sortie":"2026-08-10","langues":{"annoncees":null,"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["presentation","sortie"],"lu":"https://www.alibabacloud.com/help/en/model-studio/newly-released-models (« Realtime chat 2026-08-10 International qwen-audio-3.0-realtime-plus Qwen 3.0 Realtime Speech Model Standard Edition - next-generation duplex speech model »), 23/10/2026"},{"appuie":["presentation"],"lu":"https://www.alibabacloud.com/help/en/model-studio/newly-released-models (« Balances model intelligence with duplex dialogue rhythm for natural interaction and enhanced response quality. »), 23/10/2026"}],"classements":[{"id":"voix-a-voix/indice","nom":"Indice voix à voix d'Artificial Analysis","rang":2,"sur":12,"valeur":84.07,"unite":"points","chiffres":{"cout_par_heure_audio_entree":4.422166,"hebergeur":"Alibaba Cloud"},"voisins":["openai-gpt-live-1","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/raisonnement","nom":"Raisonnement à l'écoute, Big Bench Audio","rang":2,"sur":38,"valeur":99.2,"unite":"%","chiffres":{"cout_par_heure_audio_entree":4.422166,"hebergeur":"Alibaba Cloud"},"voisins":["stepaudio-3-realtime","phonic-1-high"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/speech-to-speech","releve":"2026-11-09"}},{"id":"voix-a-voix/conversation","nom":"Tenue de la conversation, Full Duplex Bench","rang":2,"sur":31,"valeur":98.41,"unite":"%","chiffres":{"cout_par_heure_audio_entree":4.422166,"hebergeur":"Alibaba Cloud"},"voisins":["stepaudio-3-realtime","openai-gpt-live-1"],"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":28,"sur":34,"valeur":1.54,"unite":"s","chiffres":{"cout_par_heure_audio_entree":4.422166,"hebergeur":"Alibaba Cloud"},"voisins":["step-audio-r1-1-realtime","alibaba-qwen-audio-3-0-realtime-flash"],"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":"Qwen Audio 3.0 Realtime Plus"}}