{"id":"google-gemini-2-5-pro-dec-2025","nom":"Gemini 2.5 Pro (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-pro-preview-tts","essayer":"https://aistudio.google.com/generate-speech"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/google-gemini-2-5-pro-dec-2025/","releve":"2026-10-19","en_bref":"71e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un groupe de 12 modèles trop proches pour être départagés.","presentation":"Modèle de synthèse vocale Gemini 2.5 Pro TTS, à un ou deux locuteurs, pilotable par instructions en langage naturel. Google le destine aux contenus longs et à la narration professionnelle, 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-pro-preview-tts (« Gemini 2.5 Pro TTS is best for long-form content, professional narrations, and complex creative workflows that require the highest level of vocal clarity and natural prosody. »), 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":71,"sur":96,"valeur":1037.43,"unite":"Elo","bas":1024.43,"haut":1050.43,"votes":2464,"chiffres":{"prix_par_million_caracteres":18.31,"date_sortie":"2025-12-10"},"voisins":["hume-ai-octave-tts","microsoft-azure-neural"],"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 Pro (Dec 2025)"}}