{"id":"alibaba-qwen-audio-3-0-realtime-flash","nom":"Qwen Audio 3.0 Realtime Flash","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-flash/","releve":"2026-11-09","en_bref":"6e sur 12 à l'indice voix à voix d'Artificial Analysis ; 13e sur 38 en raisonnement à l'écoute (Big Bench Audio) ; 4e sur 31 en tenue de la conversation (Full Duplex Bench) (ex æquo à valeur égale) ; 29e sur 34 au délai avant le premier son.","presentation":"Édition Flash du modèle de dialogue vocal en duplex d'Alibaba, servie par l'API Model Studio et réglée pour répondre vite. Elle s'appuie sur l'inférence parallèle et un traitement entièrement en flux.","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-flash Qwen 3.0 Realtime Speech Dialogue Model Flash Edition - a next-generation duplex speech model »), 23/10/2026"},{"appuie":["presentation"],"lu":"https://www.alibabacloud.com/help/en/model-studio/newly-released-models (« Combines high intelligence with optimized duplex rhythm for low-latency (parallel inference, full-streaming optimization) 'fast and smart' dialogue experience focusing on response speed. »), 23/10/2026"}],"classements":[{"id":"voix-a-voix/indice","nom":"Indice voix à voix d'Artificial Analysis","rang":6,"sur":12,"valeur":76.33,"unite":"points","chiffres":{"cout_par_heure_audio_entree":4.774185,"hebergeur":"Alibaba Cloud"},"voisins":["openai-gpt-realtime-2","spacexai-grok-voice-1-0"],"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":13,"sur":38,"valeur":96.1,"unite":"%","chiffres":{"cout_par_heure_audio_entree":4.774185,"hebergeur":"Alibaba Cloud"},"voisins":["openai-gpt-realtime-2","openai-gpt-realtime-2-1"],"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":4,"sur":31,"valeur":96.95,"unite":"%","chiffres":{"cout_par_heure_audio_entree":4.774185,"hebergeur":"Alibaba Cloud"},"voisins":["spacexai-grok-voice-3-0","google-gemini-3-8-live"],"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":29,"sur":34,"valeur":1.55,"unite":"s","chiffres":{"cout_par_heure_audio_entree":4.774185,"hebergeur":"Alibaba Cloud"},"voisins":["alibaba-qwen-audio-3-0-realtime-plus","alibaba-qwen3-5-omni-plus-realtime"],"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 Flash"}}