{"id":"google-gemini-2-5-flash-tts-dec-2025","nom":"Gemini 2.5 Flash TTS (Dec 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/models/gemini-2.5-flash-preview-tts","essayer":"https://aistudio.google.com/generate-speech"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/google-gemini-2-5-flash-tts-dec-2025/","releve":"2026-10-19","en_bref":"58e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un peloton de 13 modèles que la marge d'erreur ne permet pas de séparer.","presentation":"Modèle de synthèse vocale Gemini à un ou deux locuteurs, dont le style, le rythme et le ton se règlent par instructions en langage naturel. Google l'oriente vers la faible latence (assistants en temps réel, narration en volume), et sa mise à jour de décembre 2025 améliore l'expressivité et le rythme.","sortie":"2025-12-10","langues":{"annoncees":{"annoncees":"plus de 80 langues et variantes régionales, dont le français","nombre":80,"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-2.5-flash-preview-tts (« Gemini 2.5 Flash TTS is best for real-time assistants, high-volume narration, and conversational use cases that require fine-grained control over voice style and pacing. »), 17/10/2026"},{"appuie":["presentation","sortie"],"lu":"https://ai.google.dev/gemini-api/docs/changelog (« December 10, 2025 Launched enhancements to our text-to-speech models , Gemini 2.5 Flash TTS preview (optimized for low latency) and Gemini 2.5 Pro TTS preview (optimized for quality) »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://ai.google.dev/gemini-api/docs/changelog (« including enhanced expressivity, precision pacing, and seamless dialogue. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://ai.google.dev/gemini-api/docs/changelog (« Released the gemini-2.5-pro-preview-tts and gemini-2.5-flash-preview-tts models, which are capable of generating speech with one or two speakers. »), 17/10/2026"},{"appuie":["langues"],"lu":"https://docs.cloud.google.com/text-to-speech/docs/release-notes (« We just released Gemini-2.5 TTS Flash ( gemini-2.5-flash-tts ) and Pro ( gemini-2.5-pro-tts ) in GA with support for 30 speakers in 80 or more locales. »), 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":58,"sur":96,"valeur":1059.97,"unite":"Elo","bas":1047.97,"haut":1071.97,"votes":2926,"chiffres":{"prix_par_million_caracteres":9.15,"date_sortie":"2025-12-10"},"voisins":["google-chirp-3-hd","cartesia-sonic-3"],"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 2.5 Flash TTS (Dec 2025)"}}