{"id":"minimax-speech-02-turbo","nom":"MiniMax Speech 02 Turbo","editeur":"MiniMax","pays":"Chine","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://www.minimax.io/news/speech-02-series","essayer":"https://www.minimax.io/audio"},"fiche_auto":false,"page":"https://quelleia.com/voix/modeles/minimax-speech-02-turbo/","releve":"2026-10-19","en_bref":"43e sur 96 en synthèse vocale en anglais (Artificial Analysis), ex æquo avec 9 autres modèles dont les marges d'erreur se recouvrent ; 20e sur 38 en synthèse vocale en anglais (TTS Arena).","presentation":"Version à faible latence de la série Speech-02 de MiniMax, pensée pour les applications interactives en temps réel. Elle partage avec Speech-02-HD le clonage de voix à partir d'environ 10 secondes et le contrôle des émotions.","sortie":"2025-04-02","langues":{"annoncees":{"annoncees":"24 langues, dont le français","nombre":24,"francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["sortie"],"lu":"https://www.minimax.io/news/speech-02-series (« 2025.04.02 Speech-02-series : The Next Leap in Text-to-Audio and AI Voice Technology »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://www.minimax.io/news/speech-02-series (« Speech-02-Turbo: Optimized for real-time performance, balancing ultra-low latency with exceptional quality for interactive applications. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://www.minimax.io/news/speech-02-series (« Unlimited High Quality Voice Cloning: Achieve 99% vocal similarity with ultra-high fidelity in just 10 seconds of recording. »), 17/10/2026"},{"appuie":["langues"],"lu":"https://www.minimax.io/news/speech-02-series (« European & Other Languages: French, German, Spanish, Portuguese (Brazilian), Turkish, Arabic, Russian, Ukrainian and more. »), 17/10/2026"},{"appuie":["langues","presentation"],"lu":"https://platform.minimax.io/docs/guides/models-intro (« speech-02-turbo • Superior rhythm and stability • Low latency • 24 languages supported • 7 emotions supported »), 17/10/2026"}],"classements":[{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":43,"sur":96,"valeur":1091.2,"unite":"Elo","bas":1080.2,"haut":1102.2,"votes":3927,"chiffres":{"prix_par_million_caracteres":60,"date_sortie":"2025-03-31"},"voisins":["hithink-speech-2-6","openai-tts-1"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/minimax-hailou","releve":"2026-10-19"}},{"id":"synthese/tts-arena","nom":"Synthèse vocale en anglais, TTS Arena","rang":20,"sur":38,"valeur":1500,"unite":"Elo","bas":1477,"haut":1523,"votes":1231,"voisins":["inworld-tts-1-5-max","parmesan"],"source":{"nom":"TTS Arena V2","mention":"Source : TTS Arena V2, TTS-AGI","url":"https://huggingface.co/spaces/TTS-AGI/TTS-Arena-V2","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"Speech-02-Turbo","tts_arena":"MiniMax Speech 02 Turbo"}}