{"id":"fish-audio-s2-1-pro-oct-2026","nom":"Fish Audio S2.1 Pro (Oct 2026)","editeur":"Fish Audio","pays":"États-Unis","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://fish.audio/blog/s2-1-pro-free-api/","essayer":"https://fish.audio/app/text-to-speech/"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/fish-audio-s2-1-pro-oct-2026/","releve":"2026-10-19","en_bref":"18e sur 96 en synthèse vocale en anglais (Artificial Analysis), ex æquo avec 6 autres modèles dont les marges d'erreur se recouvrent.","presentation":"Modèle de synthèse vocale de production de Fish Audio, successeur de S2 Pro, avec le même pilotage par indications entre crochets et le dialogue à plusieurs locuteurs. L'éditeur annonce une meilleure qualité, une latence plus basse et un débit plus élevé que S2 Pro, et le propose aussi en version gratuite pour le développement.","sortie":"2026-06-23","langues":{"annoncees":{"annoncees":"83 langues, dont le français","nombre":83,"francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["sortie"],"lu":"https://fish.audio/blog/s2-1-pro-free-api/ (« Jun 23, 2026 · Research Fish Audio S2.1 Pro: Free Text-to-Speech API for Developers »), 17/10/2026"},{"appuie":["langues"],"lu":"https://fish.audio/blog/s2-1-pro-free-api/ (« S2.1 Pro supports 83 languages , including English, Japanese, Chinese, Korean, Spanish, Arabic, French, German, Portuguese, Russian, and dozens more. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://docs.fish.audio/developer-guide/getting-started/changelog.md (« Production text-to-speech model that improves on S2-Pro in quality, latency, and throughput. Supports 83 languages on one model, with the same `[bracket]` natural-language control and multi-speaker dialogue as S2. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://docs.fish.audio/developer-guide/models-pricing/models-overview.md (« The same model as S2.1-Pro, available at \\$0 for development and testing »), 17/10/2026"}],"classements":[{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":18,"sur":96,"valeur":1189.94,"unite":"Elo","bas":1175.94,"haut":1203.94,"votes":1929,"chiffres":{"prix_par_million_caracteres":15,"date_sortie":"2026-10-14"},"voisins":["cartesia-sonic-3-5","elevenlabs-eleven-v3"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/fishaudio","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"Fish Audio S2.1 Pro (Oct 2026)"}}