{"id":"gradium-tts-sep-2026","nom":"Gradium TTS (Sep 2026)","editeur":"Gradium","pays":"France","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://gradium.ai/text-to-speech","essayer":"https://studio.gradium.ai"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/gradium-tts-sep-2026/","releve":"2026-10-19","en_bref":"7e sur 31 en synthèse vocale en français, dans un peloton de 5 modèles que la marge d'erreur ne permet pas de séparer ; 21e sur 96 en synthèse vocale en anglais (Artificial Analysis), ex æquo avec 6 autres modèles dont les marges d'erreur se recouvrent.","presentation":"Modèle de synthèse vocale de Gradium entré en bêta publique le 22 septembre 2026 et devenu modèle par défaut le 30 septembre. Gradium annonce environ 50 millisecondes avant le premier son et une diction plus expressive que le modèle d'août.","sortie":"2026-09-30","langues":{"annoncees":{"annoncees":"5 langues (anglais, français, allemand, espagnol, portugais)","nombre":5,"francais":true,"liste":["en","fr","de","es","pt"]},"prises_en_charge_selon_open_tts":null,"evaluees":["fr","en"]},"preuves":[{"appuie":["presentation","sortie"],"lu":"https://docs.gradium.ai/guides/release-notes/2026-09 (« 2026.09.30 New TTS model Our new Text-to-Speech model is now the default, with more expressive speech and lower latency. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://docs.gradium.ai/guides/release-notes/2026-09 (« 2026.09.22 New TTS public beta Our new Text-to-Speech model entered public beta with lower latency and more expressive speech. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://gradium.ai/blog/fastest-robust-tts-model (« Our latest Text-to-Speech model takes around 50ms for the first audio chunk to arrive. »), 17/10/2026"},{"appuie":["langues"],"lu":"https://docs.gradium.ai/guides/voices/overview (« Gradium provides a curated library of flagship voices across five languages »), 17/10/2026"},{"appuie":["langues"],"lu":"https://gradium.ai/blog/gradium (« Gradium launches with real-time, multilingual (English, French, German, Spanish, Portuguese) transcription and synthesis »), 17/10/2026"}],"classements":[{"id":"synthese/francais","nom":"Synthèse vocale en français","rang":7,"sur":31,"valeur":1239.41,"unite":"Elo","bas":1216.41,"haut":1262.41,"votes":798,"chiffres":{"prix_par_million_caracteres":47.78,"date_sortie":"2026-09-22"},"voisins":["inworld-realtime-tts-2","cartesia-sonic-3-5"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/gradium","releve":"2026-10-19"}},{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":21,"sur":96,"valeur":1173.65,"unite":"Elo","bas":1159.65,"haut":1187.65,"votes":2029,"chiffres":{"prix_par_million_caracteres":47.78,"date_sortie":"2026-09-22"},"voisins":["soniox-tts-real-time-v2","minimax-speech-2-8-hd"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/gradium","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"Gradium TTS (Sep 2026)"}}