{"id":"typecast-ssfm-3-0","nom":"Typecast SSFM 3.0","editeur":"Neosapience","pays":"Corée du Sud","poids_ouverts":false,"poids_selon":"TTS Arena V2","licence":null,"licence_selon":null,"liens":{"page":"https://typecast.ai/docs/models","essayer":"https://typecast.ai/developers/api/"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/typecast-ssfm-3-0/","releve":"2026-10-19","en_bref":"22e sur 38 en synthèse vocale en anglais (TTS Arena).","presentation":"Modèle de synthèse vocale de Neosapience, utilisé dans le service Typecast et son API, avec sept préréglages d'émotion et une détection automatique de l'émotion d'après le contexte du texte. Il ajoute dix langues par rapport à la version précédente ssfm-v21.","sortie":"2026-01","langues":{"annoncees":{"annoncees":"plus de 35 langues, dont le français","nombre":35,"plus":true,"francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["langues","presentation","sortie"],"lu":"https://typecast.ai/docs/models (« ssfm-v30 2026.01 - More natural-sounding speech with smoother prosody and pacing - Emotion controls with 7 emotion presets - 35+ languages supported - Smart Emotion available »), 17/10/2026"},{"appuie":["langues"],"lu":"https://typecast.ai/docs/models (« Chinese (Mandarin), Croatian, Czech, Danish, Dutch, Finnish, French, German »), 17/10/2026"},{"appuie":["langues","presentation"],"lu":"https://typecast.ai/docs/changelog (« 37 Languages - Added 10 new languages »), 17/10/2026"}],"classements":[{"id":"synthese/tts-arena","nom":"Synthèse vocale en anglais, TTS Arena","rang":22,"sur":38,"valeur":1506,"unite":"Elo","bas":1475,"haut":1537,"votes":551,"voisins":["parmesan","cartesia-sonic-2"],"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":"Typecast SSFM 3.0"}}