{"id":"amazon-polly-neural","nom":"Polly Neural","editeur":"Amazon","pays":"États-Unis","poids_ouverts":false,"poids_selon":null,"licence":null,"licence_selon":null,"liens":{"page":"https://docs.aws.amazon.com/polly/latest/dg/neural-voices.html","essayer":"https://docs.aws.amazon.com/polly/latest/dg/what-is.html"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/amazon-polly-neural/","releve":"2026-10-19","en_bref":"90e sur 96 en synthèse vocale en anglais (Artificial Analysis), ex æquo avec 5 autres modèles dont les marges d'erreur se recouvrent.","presentation":"Moteur de synthèse vocale neuronale (NTTS) d'Amazon Polly, qui associe un modèle séquence à séquence produisant des spectrogrammes à un vocodeur neuronal. AWS le présente comme de meilleure qualité que son moteur standard par concaténation.","sortie":"2019-07-30","langues":{"annoncees":{"annoncees":"36 langues et variantes, dont le français","nombre":36,"francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["presentation"],"lu":"https://docs.aws.amazon.com/polly/latest/dg/neural-voices.html (« Amazon Polly has a Neural text-to-speech (NTTS) engine that can produce even higher quality voices than its standard voices. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://docs.aws.amazon.com/polly/latest/dg/neural-voices.html (« A neural network - that converts a sequence of phonemes (the most basic units of language) into a sequence of spectrograms . »), 17/10/2026"},{"appuie":["langues"],"lu":"https://docs.aws.amazon.com/polly/latest/dg/neural-voices.html (« Neural voices are available in 36 languages and language variants. »), 17/10/2026"},{"appuie":["langues"],"lu":"https://docs.aws.amazon.com/polly/latest/dg/neural-voices.html (« 20 French fr-FR Léa Rémi Female Male »), 17/10/2026"},{"appuie":["sortie"],"lu":"https://docs.aws.amazon.com/polly/latest/dg/doc-history.html (« Amazon Polly now provides an improved Neural TTS (NTTS) system that can provide even higher quality voices, thereby providing you with the most natural and human-like text-to-speech voices possible. »), 17/10/2026"},{"appuie":["sortie"],"lu":"https://docs.aws.amazon.com/polly/latest/dg/doc-history.html (« For more information, see Neural Text-to-Speech . July 30, 2019 »), 17/10/2026"}],"classements":[{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":90,"sur":96,"valeur":897.1,"unite":"Elo","bas":883.1,"haut":911.1,"votes":2878,"chiffres":{"prix_par_million_caracteres":16,"date_sortie":"2019-07-30"},"voisins":["rime-mist-v2","google-neural2"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/aws","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"Polly Neural"}}