{"id":"gradium-tts-aug-2026","nom":"Gradium TTS (Aug 2026)","editeur":"Gradium","pays":"France","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://gradium.ai/blog/gradium-tts-latency-and-accuracy","essayer":"https://studio.gradium.ai"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/gradium-tts-aug-2026/","releve":"2026-10-19","en_bref":"10e sur 31 en synthèse vocale en français, ex æquo avec 3 autres modèles dont les marges d'erreur se recouvrent ; 25e 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 devenu modèle par défaut le 31 août 2026, après une bêta publique ouverte le 30 juillet. Gradium le présente comme capable de lire sans prétraitement les numéros de téléphone, adresses électroniques, IBAN et codes de référence.","sortie":"2026-08-31","langues":{"annoncees":{"annoncees":"5 langues (anglais, français, espagnol, portugais, allemand)","nombre":5,"francais":true,"liste":["en","fr","es","pt","de"]},"prises_en_charge_selon_open_tts":null,"evaluees":["fr","en"]},"preuves":[{"appuie":["langues","sortie"],"lu":"https://gradium.ai/blog/gradium-tts-latency-and-accuracy (« A new Gradium TTS model is available today, and it is now the default. It passes 81.0% of a 500-sentence hard-case evaluation across five languages »), 17/10/2026"},{"appuie":["langues"],"lu":"https://gradium.ai/blog/gradium-tts-latency-and-accuracy (« 500 cases per model across English, French, Spanish, Portuguese, German. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://gradium.ai/blog/gradium-tts-latency-and-accuracy (« It reads the cases that break voice agents in production, phone numbers, email addresses, IBANs, with no pre-processing or text normalization on your side. We opened the public beta on July 30 »), 17/10/2026"},{"appuie":["sortie"],"lu":"https://docs.gradium.ai/guides/release-notes/2026-08 (« 2026.08.31 New Text-to-Speech model A new Gradium Text-to-Speech model is live and is now the default. »), 17/10/2026"}],"classements":[{"id":"synthese/francais","nom":"Synthèse vocale en français","rang":10,"sur":31,"valeur":1198.57,"unite":"Elo","bas":1177.57,"haut":1219.57,"votes":1240,"chiffres":{"prix_par_million_caracteres":47.22,"date_sortie":"2026-08-31"},"voisins":["google-gemini-3-8-flash-tts","google-gemini-3-8-flash-lite-tts"],"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":25,"sur":96,"valeur":1151.71,"unite":"Elo","bas":1138.71,"haut":1164.71,"votes":2286,"chiffres":{"prix_par_million_caracteres":47.22,"date_sortie":"2026-08-31"},"voisins":["murf-ai-falcon-2","minimax-speech-2-8-turbo"],"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 (Aug 2026)"}}