{"id":"nvidia-magpie-tts-zeroshot","nom":"Magpie TTS Zeroshot","editeur":"NVIDIA","pays":"États-Unis","poids_ouverts":true,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://build.nvidia.com/nvidia/magpie-tts-zeroshot/modelcard","essayer":"https://build.nvidia.com/nvidia/magpie-tts-zeroshot"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/nvidia-magpie-tts-zeroshot/","releve":"2026-10-19","en_bref":"30e sur 31 en synthèse vocale en français.","presentation":"Modèle de synthèse vocale de NVIDIA qui génère la voix à partir d'un court échantillon audio de référence, proposé en point d'accès sur build.nvidia.com et dans Riva. Il fonctionne en deux étapes avec un codec audio neuronal et produit une voix féminine ou masculine avec plusieurs émotions.","langues":{"annoncees":{"annoncees":"anglais (États-Unis), espagnol (Espagne) et français","nombre":3,"francais":true,"liste":["en","es","fr"]},"prises_en_charge_selon_open_tts":null,"evaluees":["fr"]},"preuves":[{"appuie":["presentation"],"lu":"https://build.nvidia.com/nvidia/magpie-tts-zeroshot (« Expressive and engaging text-to-speech, generated from a short audio sample. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://build.nvidia.com/nvidia/magpie-tts-zeroshot/modelcard (« Magpie TTS is a generative model, designed to be used as the first part of a neural text-to-speech system in conjunction with an audio codec model. »), 17/10/2026"},{"appuie":["langues","presentation"],"lu":"https://build.nvidia.com/nvidia/magpie-tts-zeroshot/modelcard (« it can output a female or a male voice for English-US and European-Spanish. In addition, it uses character-based encoding for French. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://build.nvidia.com/nvidia/magpie-tts-zeroshot/modelcard (« with two (2) emotions for the female voice and six (6) emotions for male voices »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://build.nvidia.com/nvidia/magpie-tts-zeroshot/modelcard (« Runtime Engine(s): Riva 2.19.0 or greater »), 17/10/2026"}],"classements":[{"id":"synthese/francais","nom":"Synthèse vocale en français","rang":30,"sur":31,"valeur":963.54,"unite":"Elo","bas":939.54,"haut":987.54,"votes":1251,"chiffres":{"date_sortie":"2026-07-27"},"voisins":["fish-audio-s1","openvoice-v2"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/nvidia","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"Magpie TTS Zeroshot"}}