{"id":"soniox-tts-real-time-v2","nom":"Soniox TTS Real-Time v2","editeur":"Soniox","pays":"États-Unis","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://soniox.com/blog/soniox-tts-v2/","essayer":"https://soniox.com/docs/tts/get-started"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/soniox-tts-real-time-v2/","releve":"2026-10-19","en_bref":"22e sur 31 en synthèse vocale en français, dans un peloton de 5 modèles que la marge d'erreur ne permet pas de séparer ; 20e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un groupe de 7 modèles trop proches pour être départagés.","presentation":"Soniox TTS v2 est un modèle de synthèse vocale en temps réel, servi par API, qui couvre plus de 60 langues avec une même voix. Il ajoute des balises audio pour diriger l'émotion et le jeu, ainsi que le clonage de voix.","sortie":"2026-08-11","langues":{"annoncees":{"annoncees":"plus de 60 langues, dont le français","nombre":60,"plus":true,"francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["fr","en"]},"preuves":[{"appuie":["sortie"],"lu":"https://soniox.com/blog/soniox-tts-v2/ (« August 11, 2026 by Soniox Team »), 17/10/2026"},{"appuie":["langues","presentation"],"lu":"https://soniox.com/blog/soniox-tts-v2/ (« It brings extraordinary voice quality, expressive control, exceptional precision, high-quality voice cloning, support for more than 60 languages, and low-latency streaming »), 17/10/2026"},{"appuie":["langues"],"lu":"https://soniox.com/blog/soniox-tts-v2/ (« English Spanish Japanese French German »), 17/10/2026"},{"appuie":["presentation","sortie"],"lu":"https://soniox.com/docs/tts/models (« Soniox TTS v2 is now generally available. tts-rt-v2 is available to all API customers »), 17/10/2026"}],"classements":[{"id":"synthese/francais","nom":"Synthèse vocale en français","rang":22,"sur":31,"valeur":1081.18,"unite":"Elo","bas":1048.18,"haut":1114.18,"votes":173,"chiffres":{"prix_par_million_caracteres":14.23,"date_sortie":"2026-08-12"},"voisins":["minimax-speech-2-8-turbo","voxtral-tts"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/soniox","releve":"2026-10-19"}},{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":20,"sur":96,"valeur":1179.14,"unite":"Elo","bas":1168.14,"haut":1190.14,"votes":5229,"chiffres":{"prix_par_million_caracteres":14.23,"date_sortie":"2026-08-12"},"voisins":["elevenlabs-eleven-v3","gradium-tts-sep-2026"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/soniox","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"Soniox TTS Real-Time v2"}}