{"id":"minimax-speech-2-6-hd","nom":"MiniMax Speech 2.6 HD","editeur":"MiniMax","pays":"Chine","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://www.minimax.io/news/minimax-speech-26","essayer":"https://www.minimax.io/audio"},"fiche_auto":false,"page":"https://quelleia.com/voix/modeles/minimax-speech-2-6-hd/","releve":"2026-10-19","en_bref":"32e sur 96 en synthèse vocale en anglais (Artificial Analysis), ex æquo avec 6 autres modèles dont les marges d'erreur se recouvrent ; 25e sur 38 en synthèse vocale en anglais (TTS Arena).","presentation":"Version haute qualité de Speech 2.6, la génération de synthèse vocale de MiniMax conçue pour les agents vocaux, axée sur la fidélité au timbre. Speech 2.6 lit directement adresses web, courriels, numéros de téléphone, dates et montants sans prétraitement du texte.","sortie":"2025-10-30","langues":{"annoncees":{"annoncees":"40 langues, dont le français","nombre":40,"francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["sortie"],"lu":"https://www.minimax.io/news/minimax-speech-26 (« 2025.10.30 MiniMax Speech 2.6: The Ultimate Voice Agent Has Arrived »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://www.minimax.io/news/minimax-speech-26 (« Speech 2.6 now directly converts non-standard text formats in multiple languages, including URLs, email addresses, phone numbers, dates, and monetary amounts. »), 17/10/2026"},{"appuie":["langues","presentation"],"lu":"https://platform.minimax.io/docs/guides/models-intro (« speech-2.6-hd • Ultimate Similarity • Ultra-High Quality • 40 languages supported • 7 emotions supported »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://platform.minimax.io/docs/guides/speech-t2a-websocket.md (« | speech-2.6-hd | Ultra-low latency, intelligence parsing, and enhanced naturalness. | »), 17/10/2026"},{"appuie":["langues"],"lu":"https://platform.minimax.io/docs/guides/speech-t2a-websocket.md (« | 5. French | 19. Polish | 32. Croatian | »), 17/10/2026"}],"classements":[{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":32,"sur":96,"valeur":1127.73,"unite":"Elo","bas":1116.73,"haut":1138.73,"votes":4195,"chiffres":{"prix_par_million_caracteres":100,"date_sortie":"2025-10-30"},"voisins":["async-pro-v1-0","minimax-speech-2-6-turbo"],"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":25,"sur":38,"valeur":1501,"unite":"Elo","bas":1472,"haut":1530,"votes":560,"voisins":["openaudio-s1","hithink-speech-2-6-2"],"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 2.6 HD","tts_arena":"MiniMax Speech 2.6 HD"}}