{"id":"maya-2-flash","nom":"Maya 2 Flash","editeur":"Maya Research","pays":"Inde","poids_ouverts":false,"poids_selon":null,"licence":null,"licence_selon":null,"liens":{"page":"https://mayaresearch.ai/"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/maya-2-flash/","releve":"2026-10-19","en_bref":"53e sur 96 en synthèse vocale en anglais (Artificial Analysis), ex æquo avec 12 autres modèles dont les marges d'erreur se recouvrent.","presentation":"Le modèle de synthèse vocale le plus rapide de Maya Research, conçu pour la conversation en direct. Il est servi par l'API de l'éditeur, en flux PCM 24 kHz depuis Bombay ou l'Iowa.","langues":{"annoncees":null,"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["presentation"],"lu":"https://mayaresearch.ai/ (« Maya 2 Flash The fastest model we make. Built for live conversation, where every millisecond counts. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://mayaresearch.ai/ (« Regions Mumbai · Iowa Output 24 kHz PCM, streamed »), 17/10/2026"}],"classements":[{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":53,"sur":96,"valeur":1064.86,"unite":"Elo","bas":1051.86,"haut":1077.86,"votes":2081,"chiffres":{"date_sortie":"2026-07-17"},"voisins":["minimax-t2a-01-hd","kokoro-82m-v1-0"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/maya-research","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"Maya 2 Flash"}}