{"id":"elevenlabs-turbo-v2-5","nom":"Eleven Turbo v2.5","editeur":"ElevenLabs","pays":"États-Unis","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://elevenlabs.io/blog/introducing-turbo-v25"},"fiche_auto":false,"page":"https://quelleia.com/voix/modeles/elevenlabs-turbo-v2-5/","releve":"2026-10-19","en_bref":"18e sur 31 en synthèse vocale en français, dans un peloton de 5 modèles que la marge d'erreur ne permet pas de séparer ; 40e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un groupe de 10 modèles trop proches pour être départagés ; 17e sur 38 en synthèse vocale en anglais (TTS Arena).","presentation":"Modèle de synthèse vocale à faible latence d'ElevenLabs, lancé en 2024 pour accélérer la génération dans 32 langues. L'éditeur le déclare désormais dépassé et recommande Flash v2.5, qu'il décrit comme équivalent avec une latence plus basse.","sortie":"2024-07-19","langues":{"annoncees":{"annoncees":"32 langues, dont le français","nombre":32,"francais":true},"prises_en_charge_selon_open_tts":null,"evaluees":["fr","en"]},"preuves":[{"appuie":["sortie"],"lu":"https://elevenlabs.io/blog/introducing-turbo-v25 (« Published Jul 19, 2024 »), 17/10/2026"},{"appuie":["langues","presentation"],"lu":"https://elevenlabs.io/blog/introducing-turbo-v25 (« Announcing our new Eleven Turbo 2.5 model - Hindi, French, Spanish, Mandarin and 27 other languages just got 3x faster. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://elevenlabs.io/docs/overview/models (« The eleven_turbo_v2_5 and eleven_turbo_v2 models are functionally equivalent to the eleven_flash_v2_5 and eleven_flash_v2 models respectively, except the latency on the Flash models is lower on average. »), 17/10/2026"},{"appuie":["langues","presentation"],"lu":"https://elevenlabs.io/docs/overview/models (« eleven_turbo_v2_5 First generation low-latency model (outclassed by Flash models) 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 , hu , no , vi »), 17/10/2026"}],"classements":[{"id":"synthese/francais","nom":"Synthèse vocale en français","rang":18,"sur":31,"valeur":1112.86,"unite":"Elo","bas":1091.86,"haut":1133.86,"votes":1171,"chiffres":{"prix_par_million_caracteres":50,"date_sortie":"2024-07-19"},"voisins":["elevenlabs-flash-v2-5","minimax-speech-2-8-hd"],"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":40,"sur":96,"valeur":1097.46,"unite":"Elo","bas":1087.46,"haut":1107.46,"votes":6975,"chiffres":{"prix_par_million_caracteres":50,"date_sortie":"2024-07-19"},"voisins":["step-audio-editx-mar-2026","elevenlabs-multilingual-v2"],"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":17,"sur":38,"valeur":1504,"unite":"Elo","bas":1480,"haut":1528,"votes":1139,"voisins":["deepdub-etts-3-2","elevenlabs-flash-v2-5"],"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":"Turbo v2.5","tts_arena":"Eleven Turbo v2.5"}}