{"id":"google-gemini-3-1-flash-tts","nom":"Gemini 3.1 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-3.1-flash-tts-preview","essayer":"https://aistudio.google.com/generate-speech"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/google-gemini-3-1-flash-tts/","releve":"2026-10-19","en_bref":"15e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un peloton de 6 modèles que la marge d'erreur ne permet pas de séparer.","presentation":"Modèle de synthèse vocale Gemini en préversion, à un ou plusieurs locuteurs, dont la diction se règle par des balises audio insérées dans le texte (style, rythme, accent). Google le signale désormais comme ancien modèle de préversion, remplacé par Gemini 3.8 Flash-Lite TTS.","sortie":"2026-04-15","langues":{"annoncees":{"annoncees":"plus de 70 langues, dont le français","nombre":70,"plus":true,"francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["presentation"],"lu":"https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-tts-preview (« The Gemini 3.1 Flash TTS Preview model provides powerful, low-latency speech generation with natural outputs, steerable prompts, and expressive audio tags for precise narration control. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-tts-preview (« Note: gemini-3.1-flash-tts-preview is a legacy preview model. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://ai.google.dev/gemini-api/docs/speech-generation (« Use Gemini 3.8 Flash-Lite TTS ( gemini-3.8-flash-lite-tts ) as your fast, cost-efficient workhorse replacement for gemini-3.1-flash-tts-preview . »), 17/10/2026"},{"appuie":["sortie"],"lu":"https://ai.google.dev/gemini-api/docs/changelog (« April 15, 2026 Launched Gemini 3.1 Flash TTS Preview , our cost-efficient, expressive, and steerable text to speech model. »), 17/10/2026"},{"appuie":["langues","presentation"],"lu":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-1-flash-tts/ (« The model stands out further with native multi-speaker dialogue, support for 70+ languages, and granular creative control via natural language. »), 17/10/2026"},{"appuie":["langues"],"lu":"https://docs.cloud.google.com/text-to-speech/docs/gemini-tts (« Gemini-TTS includes the following available models: Gemini 3.1 Flash TTS (Preview) Model ID gemini-3.1-flash-tts-preview »), 17/10/2026"},{"appuie":["langues"],"lu":"https://docs.cloud.google.com/text-to-speech/docs/gemini-tts (« English (United States) en-US GA French (France) fr-FR GA »), 17/10/2026"}],"classements":[{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":15,"sur":96,"valeur":1212.58,"unite":"Elo","bas":1201.58,"haut":1223.58,"votes":4143,"chiffres":{"prix_par_million_caracteres":18.31,"date_sortie":"2026-04-15"},"voisins":["stepaudio-2-5-tts-aug-2026","elevenlabs-v3-conversational"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/gemini-tts","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"Gemini 3.1 Flash TTS"}}