{"id":"breeze-tts-2","nom":"Breeze TTS 2","editeur":"BreezeBlue","pays":null,"poids_ouverts":true,"poids_selon":null,"licence":"BreezeBlue Research and Non-Commercial License (poids réservés à la recherche et à l'usage non commercial)","licence_selon":null,"liens":{"page":"https://breezeblue.ai/breeze-tts-2","essayer":"https://huggingface.co/spaces/BreezeBlue/breeze-tts-2-demo"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/breeze-tts-2/","releve":"2026-10-19","en_bref":"11e 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 pensé pour l'interaction en temps réel, qui réunit conception de voix à partir d'une description en langage naturel, direction du jeu vocal et génération en flux continu. Il gère aussi le clonage de voix et des événements vocaux insérés dans le texte (rire, toux, soupir).","sortie":"2026-08-07","langues":{"annoncees":{"annoncees":"51 langues dont le français (service BreezeBlue) ; anglais et chinois pour les poids ouverts","nombre":51,"francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["presentation"],"lu":"https://huggingface.co/BreezeBlue/Breeze-TTS-2/raw/main/README.md (« Breeze TTS 2 is an open-weight text-to-speech model built for real-time interaction. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://breezeblue.ai/breeze-tts-2 (« Breeze TTS 2 brings natural-language voice design, voice direction for any voice, and low-latency streaming generation together in a single model. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/BreezeBlue/Breeze-TTS-2/raw/main/README.md (« Adds expressive inline events directly in the text: use parentheses in English, such as `(laugh)`, `(cough)`, `(clears throat)`, and `(sigh)` »), 17/10/2026"},{"appuie":["sortie"],"lu":"https://breezeblue.ai/breeze-tts-2 (« Introducing Breeze TTS 2 Real-time voice intelligence that brings every character to life. August 7, 2026 »), 17/10/2026"},{"appuie":["langues"],"lu":"https://breezeblue.ai/breeze-tts-2 (« Create natural, expressive text to speech AI voices across 51 languages »), 17/10/2026"},{"appuie":["langues"],"lu":"https://breezeblue.ai/breeze-tts-2 (« Choose a language English Español 中文 日本語 Français »), 17/10/2026"},{"appuie":["langues"],"lu":"https://huggingface.co/BreezeBlue/Breeze-TTS-2/raw/main/README.md (« Generates natural English and Chinese speech with a single model. »), 17/10/2026"}],"classements":[{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":11,"sur":96,"valeur":1221.99,"unite":"Elo","bas":1207.99,"haut":1235.99,"votes":2138,"chiffres":{"prix_par_million_caracteres":34,"date_sortie":"2026-08-23"},"voisins":["fish-audio-drama-3-preview","inworld-realtime-tts-2-flash"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/breeze-blue","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"Breeze TTS 2"}}