{"id":"elevenlabs-multilingual-v2","nom":"Eleven Multilingual v2","editeur":"ElevenLabs","pays":"États-Unis","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://elevenlabs.io/docs/overview/models","essayer":"https://elevenlabs.io/text-to-speech"},"fiche_auto":false,"page":"https://quelleia.com/voix/modeles/elevenlabs-multilingual-v2/","releve":"2026-10-19","en_bref":"13e sur 31 en synthèse vocale en français, dans un peloton de 5 modèles que la marge d'erreur ne permet pas de séparer ; 41e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un peloton de 10 modèles que la marge d'erreur ne permet pas de séparer ; 15e sur 38 en synthèse vocale en anglais (TTS Arena).","presentation":"Modèle de synthèse vocale multilingue d'ElevenLabs, sorti en 2023, qui privilégie une voix naturelle et une qualité stable sur les textes longs. L'éditeur le range désormais dans la génération précédente, avec une latence et un coût par caractère plus élevés que les modèles Flash.","sortie":"2023-08-22","langues":{"annoncees":{"annoncees":"29 langues, dont le français","nombre":29,"francais":true,"liste":["en","ja","zh","de","hi","fr","ko","pt","it","es","id","nl","tr","fil","pl","sv","bg","ro","ar","cs","el","fi","hr","ms","sk","da","ta","uk","ru"]},"prises_en_charge_selon_open_tts":null,"evaluees":["fr","en"]},"preuves":[{"appuie":["sortie"],"lu":"https://elevenlabs.io/blog/eleven-multilingual-v2 (« Published Aug 22, 2023 »), 17/10/2026"},{"appuie":["langues","presentation","sortie"],"lu":"https://elevenlabs.io/blog/eleven-multilingual-v2 (« We are excited to introduce Eleven Multilingual v2, our latest state-of-the-art speech synthesis model. With unparalleled speech synthesis capabilities, Eleven Multilingual v2 supports 29 languages. »), 17/10/2026"},{"appuie":["langues","presentation"],"lu":"https://elevenlabs.io/docs/overview/models (« Eleven Multilingual v2 Lifelike, consistent quality speech synthesis model Natural-sounding output 29 languages supported 10,000 character limit Most stable on long-form generations »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://elevenlabs.io/docs/overview/models (« While it has a higher latency & cost per character than Flash models, it delivers superior quality for projects where lifelike speech is important. »), 17/10/2026"},{"appuie":["langues"],"lu":"https://elevenlabs.io/docs/overview/models (« eleven_multilingual_v2 Our lifelike model with rich emotional expression en , ja , zh , de , hi , fr , ko , pt , it , es , id , nl , tr , fil , pl , sv , bg , ro , ar , cs , el , fi , hr , ms , sk , da , ta , uk , ru »), 17/10/2026"}],"classements":[{"id":"synthese/francais","nom":"Synthèse vocale en français","rang":13,"sur":31,"valeur":1162.32,"unite":"Elo","bas":1141.32,"haut":1183.32,"votes":1137,"chiffres":{"prix_par_million_caracteres":100,"date_sortie":"2023-08-22"},"voisins":["alibaba-qwen-audio-3-0-tts-plus","inworld-realtime-tts-2-flash"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/elevenlabs","releve":"2026-10-19"}},{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":41,"sur":96,"valeur":1095.84,"unite":"Elo","bas":1085.84,"haut":1105.84,"votes":7429,"chiffres":{"prix_par_million_caracteres":100,"date_sortie":"2023-08-22"},"voisins":["elevenlabs-turbo-v2-5","hithink-speech-2-6"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/elevenlabs","releve":"2026-10-19"}},{"id":"synthese/tts-arena","nom":"Synthèse vocale en anglais, TTS Arena","rang":15,"sur":38,"valeur":1504,"unite":"Elo","bas":1482,"haut":1526,"votes":1144,"voisins":["fish-audio-openaudio-s2","deepdub-etts-3-2"],"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":{"artificial_analysis":"Multilingual v2","tts_arena":"Eleven Multilingual v2"}}