{"id":"gradium-tts-pre-2026-08","nom":"Gradium TTS (pre-2026.08)","editeur":"Gradium","pays":"France","poids_ouverts":false,"poids_selon":"TTS Arena V2","licence":null,"licence_selon":null,"liens":{"page":"https://docs.gradium.ai/guides/release-notes/2026-06"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/gradium-tts-pre-2026-08/","releve":"2026-10-19","en_bref":"10e sur 38 en synthèse vocale en anglais (TTS Arena).","presentation":"Génération du modèle de synthèse vocale de Gradium en service avant la version du 31 août 2026. Les notes de version de juin 2026 décrivent ce modèle par défaut comme plus expressif et plus fiable pour épeler adresses, numéros et sigles.","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":["en"]},"preuves":[{"appuie":["presentation"],"lu":"https://docs.gradium.ai/guides/release-notes/2026-06 (« Gradium TTS now runs on an upgraded default model focused on more expressive speech and better reliable pronunciation for production voice agents. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://docs.gradium.ai/guides/release-notes/2026-08 (« A new Gradium Text-to-Speech model is live and is now the default. »), 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/tts-arena","nom":"Synthèse vocale en anglais, TTS Arena","rang":10,"sur":38,"valeur":1520,"unite":"Elo","bas":1489,"haut":1551,"votes":563,"voisins":["smallest-ai-lightning-v3-1-pro","minimax-speech-2-8-turbo"],"source":{"nom":"TTS Arena V2","mention":"Source : TTS Arena V2, TTS-AGI","url":"https://huggingface.co/spaces/TTS-AGI/TTS-Arena-V2","releve":"2026-10-19"}}],"noms_dans_les_sources":{"tts_arena":"Gradium TTS (pre-2026.08)"}}