{"id":"google-gemini-3-8-live","nom":"Gemini 3.8 Live","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/models/gemini-3.8-live","essayer":"https://ai.google.dev/gemini-api/docs/live-guide"},"fiche_auto":false,"page":"https://quelleia.com/voix/modeles/google-gemini-3-8-live/","releve":"2026-11-09","en_bref":"16e sur 38 en raisonnement à l'écoute (Big Bench Audio) ; 6e sur 31 en tenue de la conversation (Full Duplex Bench) (ex æquo à valeur égale) ; 20e sur 34 au délai avant le premier son.","presentation":"Modèle audio vers audio de Google pour les agents vocaux à faible latence, servi par l'API Live, avec un raisonnement entrelacé à la parole sans délai de réflexion. Il appelle les fonctions de façon asynchrone par défaut.","sortie":"2026-09-15","langues":{"annoncees":{"annoncees":"99 langues pour l'API Live, dont le français","nombre":99,"francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["presentation","sortie"],"lu":"https://ai.google.dev/gemini-api/docs/changelog (« September 15, 2026 Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking generally available (GA) : Released two new audio-to-audio models for real-time voice applications using the Live API: Gemini 3.8 Live ( gemini-3.8-live ): The default option for most low-latency voice agent experiences and real-time dialogue without reasoning delays. Features interleaved reasoning, default asynchronous function calling, and full session client content updates. »), 23/10/2026"},{"appuie":["presentation"],"lu":"https://ai.google.dev/gemini-api/docs/models/gemini-3.8-live (« Gemini 3.8 Live delivers ultra-low latency audio-to-audio interactions and expands support for asynchronous workflows. »), 23/10/2026"},{"appuie":["langues"],"lu":"https://ai.google.dev/gemini-api/docs/live-guide (« Supported languages Live API supports the following 99 languages. »), 23/10/2026"},{"appuie":["langues"],"lu":"https://ai.google.dev/gemini-api/docs/live-guide (« French fr »), 23/10/2026"}],"classements":[{"id":"voix-a-voix/raisonnement","nom":"Raisonnement à l'écoute, Big Bench Audio","rang":16,"sur":38,"valeur":91.7,"unite":"%","chiffres":{"cout_par_heure_audio_entree":0.8413271351714341,"hebergeur":"Google"},"voisins":["spacexai-grok-voice-fast-1-0","google-gemini-2-5-flash-native-audio-dialog-thinking"],"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":6,"sur":31,"valeur":96.11,"unite":"%","chiffres":{"cout_par_heure_audio_entree":0.8413271351714341,"hebergeur":"Google"},"voisins":["alibaba-qwen-audio-3-0-realtime-flash","openai-gpt-realtime-2"],"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":20,"sur":34,"valeur":1.177,"unite":"s","chiffres":{"cout_par_heure_audio_entree":0.8413271351714341,"hebergeur":"Google"},"voisins":["amazon-nova-2-sonic","openai-gpt-live-1"],"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 3.8 Live"}}