{"id":"openmoss-team-moss-tts","nom":"MOSS-TTS","editeur":"OpenMOSS","pays":"Chine","poids_ouverts":true,"poids_selon":null,"licence":"Apache 2.0","licence_selon":null,"liens":{"page":"https://github.com/OpenMOSS/MOSS-TTS","essayer":"https://huggingface.co/spaces/OpenMOSS-Team/MOSS-TTS"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/openmoss-team-moss-tts/","releve":"2026-10-19","en_bref":"8e sur 16 en prononciation du français.","presentation":"MOSS-TTS est le modèle principal de la famille de synthèse vocale MOSS-TTS, centré sur le clonage de voix sans entraînement préalable et la génération de longs textes de façon stable. Il permet de régler finement la prononciation (pinyin, phonèmes) et la durée, et de mêler plusieurs langues dans une même phrase.","taille":"8 milliards de paramètres","langues":{"annoncees":{"annoncees":"20 langues, dont le français","nombre":20,"francais":true,"liste":["zh","en","de","es","fr","ja","it","he","ko","ru","fa","ar","pl","pt","cs","da","sv","hu","el","tr"]},"prises_en_charge_selon_open_tts":20,"evaluees":["fr"]},"preuves":[{"appuie":["presentation"],"lu":"https://huggingface.co/OpenMOSS-Team/MOSS-TTS/raw/main/README.md (« MOSS‑TTS: The flagship production model featuring high fidelity and optimal zero-shot voice cloning. It supports long-speech generation, fine-grained control over Pinyin, phonemes, and duration, as well as multilingual/code-switched synthesis. »), 17/10/2026"},{"appuie":["langues"],"lu":"https://huggingface.co/OpenMOSS-Team/MOSS-TTS/raw/main/README.md (« MOSS-TTS, MOSS-TTSD and MOSS-TTS-Realtime currently supports 20 languages: »), 17/10/2026"},{"appuie":["langues"],"lu":"https://huggingface.co/OpenMOSS-Team/MOSS-TTS/raw/main/README.md (« | Spanish | es | 🇪🇸 | French | fr | 🇫🇷 | »), 17/10/2026"},{"appuie":["taille"],"lu":"https://huggingface.co/OpenMOSS-Team/MOSS-TTS/raw/main/README.md (« | MOSS-TTS | MossTTSDelay | 8B | »), 17/10/2026"}],"classements":[{"id":"synthese/prononciation","nom":"Prononciation du français","rang":8,"sur":16,"valeur":6.11,"unite":"%","chiffres":{"rtfx":23.86,"taille_milliards":8.49,"langues":20,"clonage":true},"voisins":["alibaba-qwen3-tts-12hz-1-7b-customvoice","nvidia-magpie-multilingual-357m-feb-2026"],"source":{"nom":"Open TTS Leaderboard","mention":"Source : Open TTS Leaderboard, Hugging Face","url":"https://huggingface.co/spaces/hf-audio/open_tts_leaderboard","releve":"2026-10-19"}}],"noms_dans_les_sources":{"hf_audio":"OpenMOSS-Team/MOSS-TTS"}}