{"id":"minimax-speech-2-8-hd","nom":"MiniMax Speech 2.8 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-28","essayer":"https://www.minimax.io/audio"},"fiche_auto":false,"page":"https://quelleia.com/voix/modeles/minimax-speech-2-8-hd/","releve":"2026-10-19","en_bref":"19e sur 31 en synthèse vocale en français, dans un groupe de 5 modèles trop proches pour être départagés ; 21e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un groupe de 7 modèles trop proches pour être départagés ; 7e sur 38 en synthèse vocale en anglais (TTS Arena).","presentation":"Modèle de synthèse vocale de MiniMax qui ajoute des balises sonores (rires, respirations, raclements de gorge) et reproduit les hésitations de la parole naturelle. Il clone une voix à partir d'un échantillon de 10 secondes et vise une sortie sans bruit de fond ni artefact.","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":["presentation"],"lu":"https://www.minimax.io/news/minimax-speech-28 (« Speech 2.8 introduces Native Sound Tags. By modeling colloquial fillers like \"um,\" \"uh,\" and \"ah,\" we preserve the natural rhythm, pitch, and pauses of human dialogue. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://www.minimax.io/news/minimax-speech-28 (« With just a 10-second sample, Speech 2.8 precisely captures your unique texture, breathiness, and even your specific speaking pace. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://www.minimax.io/news/minimax-speech-28 (« We've re-engineered our processing engine to eliminate background noise and synthetic distortion. »), 17/10/2026"},{"appuie":["langues","presentation"],"lu":"https://platform.minimax.io/docs/guides/models-intro (« speech-2.8-hd • Ultra-realistic quality featuring sound tags • 40 languages supported • 7 emotions supported »), 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"},{"appuie":["presentation"],"lu":"https://platform.minimax.io/docs/release-notes/models.md (« Natural Sound Tags, lifelike voice, pristine audio quality »), 17/10/2026"}],"classements":[{"id":"synthese/francais","nom":"Synthèse vocale en français","rang":19,"sur":31,"valeur":1112.09,"unite":"Elo","bas":1091.09,"haut":1133.09,"votes":1185,"chiffres":{"prix_par_million_caracteres":100,"date_sortie":"2026-02-14"},"voisins":["elevenlabs-turbo-v2-5","cartesia-sonic-3"],"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":21,"sur":96,"valeur":1173.51,"unite":"Elo","bas":1162.51,"haut":1184.51,"votes":5043,"chiffres":{"prix_par_million_caracteres":100,"date_sortie":"2026-02-14"},"voisins":["gradium-tts-sep-2026","smallest-ai-lightning-v3-1-pro-jul-2026"],"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":7,"sur":38,"valeur":1535,"unite":"Elo","bas":1505,"haut":1565,"votes":503,"voisins":["star-june-2026","hume-octave"],"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 HD","tts_arena":"MiniMax Speech 2.8 HD"}}