{"id":"google-wavenet","nom":"WaveNet","editeur":"Google","pays":"États-Unis","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://docs.cloud.google.com/text-to-speech/docs/list-voices-and-types","essayer":"https://cloud.google.com/text-to-speech"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/google-wavenet/","releve":"2026-10-19","en_bref":"87e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un peloton de 6 modèles que la marge d'erreur ne permet pas de séparer.","presentation":"Voix de synthèse de Google Cloud Text-to-Speech produites par les modèles WaveNet de DeepMind, entraînés sur des enregistrements bruts de voix humaines. Google les a lancées avec le service Cloud Text-to-Speech en 2018 et les classe parmi ses voix généralistes.","sortie":"2018-03-28","langues":{"annoncees":{"annoncees":"liste de langues publiée par Google, dont le français","francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["presentation"],"lu":"https://docs.cloud.google.com/text-to-speech/docs/list-voices-and-types (« WaveNet models have been trained using raw audio samples of actual humans speaking. »), 17/10/2026"},{"appuie":["presentation","sortie"],"lu":"https://cloud.google.com/blog/products/gcp/introducing-cloud-text-to-speech-powered-by-deepmind-wavenet-technology (« Introducing Cloud Text-to-Speech powered by DeepMind WaveNet technology March 28, 2018 »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://docs.cloud.google.com/text-to-speech/docs/list-voices-and-types (« WaveNet General purpose »), 17/10/2026"},{"appuie":["langues"],"lu":"https://docs.cloud.google.com/text-to-speech/docs/list-voices-and-types (« French (France) Premium fr-FR fr-FR-Wavenet-F FEMALE »), 17/10/2026"}],"classements":[{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":87,"sur":96,"valeur":918.02,"unite":"Elo","bas":906.02,"haut":930.02,"votes":6306,"chiffres":{"prix_par_million_caracteres":4,"date_sortie":"2016-09-08"},"voisins":["kugel-3","coqui-xtts-v2"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/google","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"WaveNet"}}