{"id":"deepgram-flux-tts","nom":"Flux TTS","editeur":"Deepgram","pays":"États-Unis","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://developers.deepgram.com/docs/flux-tts/overview","essayer":"https://playground.deepgram.com/"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/deepgram-flux-tts/","releve":"2026-10-19","en_bref":"63e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un groupe de 12 modèles trop proches pour être départagés.","presentation":"Flux TTS est le modèle de synthèse vocale de Deepgram conçu pour les agents vocaux, en flux continu (WebSocket) ou par lot (REST), qui garde le ton d'un tour de parole à l'autre. Il signale le texte réellement prononcé quand l'utilisateur coupe la parole et n'existe pour l'instant qu'en anglais.","sortie":"2026-08-12","langues":{"annoncees":{"annoncees":"anglais seulement","nombre":1,"francais":false,"liste":["en"]},"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["sortie"],"lu":"https://developers.deepgram.com/changelog/2026/8/19 (« Flux TTS , which reached general availability on 12 August »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://developers.deepgram.com/docs/flux-tts/overview.md (« It is served on the `/v2/speak` endpoint and shares one set of Flux voices across two transports. When a user barges in, `Interrupt` reports exactly what they heard (`text_spoken`) »), 17/10/2026"},{"appuie":["langues"],"lu":"https://developers.deepgram.com/docs/tts-models-languages-overview (« Flux TTS is English-only today »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://developers.deepgram.com/docs/tts-models-languages-overview (« It's conversation-native: streaming-first, turn-based, expressive by default, and consistent across turns, with native interruption handling »), 17/10/2026"}],"classements":[{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":63,"sur":96,"valeur":1052.07,"unite":"Elo","bas":1039.07,"haut":1065.07,"votes":2116,"chiffres":{"prix_par_million_caracteres":45,"date_sortie":"2026-08-12"},"voisins":["xiaomi-mimo-v2-5-tts","async-flash-v1-0"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/deepgram","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"Flux TTS"}}