{"id":"maya1","nom":"Maya1","editeur":"Maya Research","pays":"Inde","poids_ouverts":true,"poids_selon":null,"licence":"Apache 2.0","licence_selon":null,"liens":{"page":"https://huggingface.co/maya-research/maya1","essayer":"https://huggingface.co/spaces/maya-research/maya1"},"fiche_auto":false,"page":"https://quelleia.com/voix/modeles/maya1/","releve":"2026-10-19","en_bref":"66e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un groupe de 12 modèles trop proches pour être départagés ; 36e sur 38 en synthèse vocale en anglais (TTS Arena).","presentation":"Modèle de synthèse vocale à poids ouverts de Maya Research, où la voix se décrit en langage naturel (âge, accent, timbre, débit) au lieu d'être choisie dans une liste. Des balises insérées dans le texte déclenchent plus de 20 émotions et effets vocaux, comme le rire.","taille":"3,3 milliards de paramètres","langues":{"annoncees":null,"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["presentation"],"lu":"https://huggingface.co/maya-research/maya1/raw/main/README.md (« **Maya-1 is an open-weight text-to-speech model from Maya Research that combines natural-language voice descriptions with inline expressive controls.** »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/maya-research/maya1/raw/main/README.md (« | Published expressive range | More than 20 emotions and vocal styles, as described in the release | »), 17/10/2026"},{"appuie":["taille"],"lu":"https://huggingface.co/maya-research/maya1/raw/main/README.md (« | Parameters | Approximately 3.30 billion; Hub tensor metadata reports 3,300,928,512 parameters | »), 17/10/2026"}],"classements":[{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":66,"sur":96,"valeur":1046.22,"unite":"Elo","bas":1034.22,"haut":1058.22,"votes":3301,"chiffres":{"date_sortie":"2025-06-25"},"voisins":["maya-2-global","fish-audio-openaudio-s1-mini"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/maya-research","releve":"2026-10-19"}},{"id":"synthese/tts-arena","nom":"Synthèse vocale en anglais, TTS Arena","rang":36,"sur":38,"valeur":1406,"unite":"Elo","bas":1370,"haut":1442,"votes":467,"voisins":["silk-mulberry-1-5","wordcab-tts"],"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":"Maya1","tts_arena":"Maya 1"}}