{"id":"google-gemini-3-8-flash-tts","nom":"Gemini 3.8 Flash TTS","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-flash-tts","essayer":"https://aistudio.google.com/generate-speech"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/google-gemini-3-8-flash-tts/","releve":"2026-10-19","en_bref":"9e sur 31 en synthèse vocale en français, dans un groupe de 4 modèles trop proches pour être départagés ; 5e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un peloton de 3 modèles que la marge d'erreur ne permet pas de séparer.","presentation":"Modèle de synthèse vocale principal de la gamme Gemini 3.8, à un ou plusieurs locuteurs, avec création de voix par description et reproduction d'une voix à partir d'un enregistrement. Google le destine aux productions créatives, aux accents régionaux et aux narrations longues à voix stable.","sortie":"2026-09-22","langues":{"annoncees":{"annoncees":"plus de 130 langues, dont le français","nombre":130,"plus":true,"francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["fr","en"]},"preuves":[{"appuie":["presentation"],"lu":"https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash-tts (« Gemini 3.8 Flash TTS ( gemini-3.8-flash-tts ) is Google's flagship creative text-to-speech model, engineered for studio-grade voice fidelity, expressive acting, authentic regional accents, and rock-solid long-form multi-turn stability. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://ai.google.dev/gemini-api/docs/speech-generation (« Gemini 3.8 Flash TTS ( gemini-3.8-flash-tts ) ✔️ ✔️ ✔️ ✔️ »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://ai.google.dev/gemini-api/docs/speech-generation (« Model Single speaker Multi-speaker Voice design Voice replication »), 17/10/2026"},{"appuie":["sortie"],"lu":"https://ai.google.dev/gemini-api/docs/changelog (« September 22, 2026 Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS generally available (GA) »), 17/10/2026"},{"appuie":["langues"],"lu":"https://ai.google.dev/gemini-api/docs/speech-generation (« Gemini 3.8 Flash TTS ( gemini-3.8-flash-tts ) supports over 130 languages »), 17/10/2026"},{"appuie":["langues"],"lu":"https://ai.google.dev/gemini-api/docs/speech-generation (« Finnish ✔️ - French ✔️ ✔️ Galician »), 17/10/2026"}],"classements":[{"id":"synthese/francais","nom":"Synthèse vocale en français","rang":9,"sur":31,"valeur":1204.69,"unite":"Elo","bas":1183.69,"haut":1225.69,"votes":1372,"chiffres":{"prix_par_million_caracteres":16.49,"date_sortie":"2026-09-23"},"voisins":["cartesia-sonic-3-5","gradium-tts-aug-2026"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/gemini","releve":"2026-10-19"}},{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":5,"sur":96,"valeur":1278.21,"unite":"Elo","bas":1263.21,"haut":1293.21,"votes":2806,"chiffres":{"prix_par_million_caracteres":16.49,"date_sortie":"2026-09-23"},"voisins":["cartesia-sonic-3-6","alibaba-qwen-audio-3-0-tts-plus"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/gemini","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"Gemini 3.8 Flash TTS"}}