{"id":"google-gemini-2-5-flash-native-audio-preview-09-2025","nom":"Gemini 2.5 Flash Native Audio Preview (Sep 2025)","editeur":"Google","pays":"États-Unis","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://ai.google.dev/gemini-api/docs/changelog"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/google-gemini-2-5-flash-native-audio-preview-09-2025/","releve":"2026-11-09","en_bref":"31e sur 31 en tenue de la conversation (Full Duplex Bench).","presentation":"Version de septembre 2025 du modèle à sortie audio native de Gemini 2.5 Flash pour l'API Live. Elle améliore l'appel de fonctions et la gestion des coupures de parole.","sortie":"2025-09-23","langues":{"annoncees":null,"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["presentation","sortie"],"lu":"https://ai.google.dev/gemini-api/docs/changelog (« September 23, 2025 Released gemini-2.5-flash-native-audio-preview-09-2025 , a new native audio model for the Live API with improved function calling and speech cut off handling. »), 23/10/2026"}],"classements":[{"id":"voix-a-voix/conversation","nom":"Tenue de la conversation, Full Duplex Bench","rang":31,"sur":31,"valeur":30.34,"unite":"%","chiffres":{"hebergeur":"Google"},"voisins":["google-gemini-2-5-flash-native-audio-preview-12-2025"],"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":"Gemini 2.5 Flash Native Audio Preview (Sep 2025)"}}