{"id":"stepaudio-2-5-tts-aug-2026","nom":"StepAudio 2.5 TTS (Aug 2026)","editeur":"StepFun","pays":"Chine","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://platform.stepfun.ai/docs/en/guides/models/stepaudio-2.5-tts","essayer":"https://audio.stepfun.ai/"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/stepaudio-2-5-tts-aug-2026/","releve":"2026-10-19","en_bref":"14e sur 96 en synthèse vocale en anglais (Artificial Analysis), ex æquo avec 5 autres modèles dont les marges d'erreur se recouvrent.","presentation":"Modèle de synthèse vocale de StepFun piloté par des consignes en langage naturel, à la fois pour l'ensemble d'un passage et phrase par phrase (émotion, pauses, respiration). Il clone une voix à partir d'environ 3 secondes d'audio de référence.","langues":{"annoncees":null,"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["presentation"],"lu":"https://platform.stepfun.ai/docs/en/guides/models/stepaudio-2.5-tts.md (« StepFun's first speech synthesis model to integrate contextual understanding into the entire speech generation pipeline. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://platform.stepfun.ai/docs/en/guides/models/audio.md (« Instead of matching preset tags, you describe the delivery you want in natural language, at two levels: »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://platform.stepfun.ai/docs/en/guides/models/audio.md (« Zero-shot voice cloning**: about 3 seconds of reference audio is enough to clone a voice precisely »), 17/10/2026"}],"classements":[{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":14,"sur":96,"valeur":1215.78,"unite":"Elo","bas":1201.78,"haut":1229.78,"votes":2028,"chiffres":{"prix_par_million_caracteres":85,"date_sortie":"2026-08-26"},"voisins":["vui-labs-luna-tts","google-gemini-3-1-flash-tts"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/stepfun","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"StepAudio 2.5 TTS (Aug 2026)"}}