{"id":"minimax-speech-2-8-turbo","nom":"MiniMax Speech 2.8 Turbo","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-28","essayer":"https://www.minimax.io/audio"},"fiche_auto":false,"page":"https://quelleia.com/voix/modeles/minimax-speech-2-8-turbo/","releve":"2026-10-19","en_bref":"21e sur 31 en synthèse vocale en français, dans un peloton de 5 modèles que la marge d'erreur ne permet pas de séparer ; 25e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un peloton de 7 modèles que la marge d'erreur ne permet pas de séparer ; 11e sur 38 en synthèse vocale en anglais (TTS Arena).","presentation":"Version rapide de Speech 2.8 de MiniMax, qui accepte les mêmes balises sonores comme les rires ou les respirations. L'éditeur la présente comme un compromis entre vitesse et débit naturel.","sortie":"2026-01-23","langues":{"annoncees":{"annoncees":"40 langues, dont le français","nombre":40,"francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["fr","en"]},"preuves":[{"appuie":["sortie"],"lu":"https://www.minimax.io/news/minimax-speech-28 (« 2026.1.23 MiniMax Speech 2.8: Breathing life into AI voice »), 17/10/2026"},{"appuie":["langues","presentation"],"lu":"https://platform.minimax.io/docs/guides/models-intro (« speech-2.8-turbo • Seamless speed meets natural flow • 40 languages supported • 7 emotions supported »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://platform.minimax.io/docs/api-reference/speech-t2a-http.md (« Only supported when using `speech-2.8-hd` or `speech-2.8-turbo` models. Supported interjections: `(laughs)`, »), 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/francais","nom":"Synthèse vocale en français","rang":21,"sur":31,"valeur":1088.9,"unite":"Elo","bas":1067.9,"haut":1109.9,"votes":1219,"chiffres":{"prix_par_million_caracteres":60,"date_sortie":"2026-02-14"},"voisins":["cartesia-sonic-3","soniox-tts-real-time-v2"],"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/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":25,"sur":96,"valeur":1152.48,"unite":"Elo","bas":1141.48,"haut":1163.48,"votes":4823,"chiffres":{"prix_par_million_caracteres":60,"date_sortie":"2026-02-14"},"voisins":["gradium-tts-aug-2026","spacexai-tts"],"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":11,"sur":38,"valeur":1519,"unite":"Elo","bas":1490,"haut":1548,"votes":533,"voisins":["gradium-tts-pre-2026-08","minimax-speech-02-hd"],"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 2.8 Turbo","tts_arena":"MiniMax Speech 2.8 Turbo"}}