{"id":"elevenlabs-flash-v2-5","nom":"Eleven Flash v2.5","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-flash-v2-5/","releve":"2026-10-19","en_bref":"17e sur 31 en synthèse vocale en français, dans un peloton de 5 modèles que la marge d'erreur ne permet pas de séparer ; 49e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un groupe de 13 modèles trop proches pour être départagés ; 18e sur 38 en synthèse vocale en anglais (TTS Arena).","presentation":"Modèle de synthèse vocale rapide d'ElevenLabs, conçu pour les agents vocaux et les usages en temps réel, avec une latence annoncée d'environ 75 ms. Il coûte deux fois moins cher par caractère en API, avec une qualité et une profondeur émotionnelle un peu inférieures aux modèles Turbo.","sortie":"2024-12-18","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/meet-flash (« Published Dec 18, 2024 »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://elevenlabs.io/blog/meet-flash (« It has a slightly lower quality and emotional depth that the Turbo models but significantly lower latency. »), 17/10/2026"},{"appuie":["langues","presentation"],"lu":"https://elevenlabs.io/docs/overview/models (« Eleven Flash v2.5 Our fast, affordable speech synthesis model Ultra-low latency (~75ms†) 32 languages supported 40,000 character limit Faster model, 50% lower price per character for API generations »), 17/10/2026"},{"appuie":["langues"],"lu":"https://elevenlabs.io/docs/overview/models (« Flash v2.5 supports 32 languages - all languages from v2 models plus: Hungarian, Norwegian & Vietnamese »), 17/10/2026"},{"appuie":["langues"],"lu":"https://elevenlabs.io/docs/overview/models (« Our multilingual v2 models support 29 languages: English (USA, UK, Australia, Canada), Japanese, Chinese, German, Hindi, French (France, Canada) »), 17/10/2026"}],"classements":[{"id":"synthese/francais","nom":"Synthèse vocale en français","rang":17,"sur":31,"valeur":1131.33,"unite":"Elo","bas":1110.33,"haut":1152.33,"votes":1173,"chiffres":{"prix_par_million_caracteres":50,"date_sortie":"2024-12-18"},"voisins":["spacexai-tts","elevenlabs-turbo-v2-5"],"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":49,"sur":96,"valeur":1078.27,"unite":"Elo","bas":1067.27,"haut":1089.27,"votes":5805,"chiffres":{"prix_par_million_caracteres":50,"date_sortie":"2024-12-18"},"voisins":["google-studio","openai-gpt-realtime-2"],"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":18,"sur":38,"valeur":1505,"unite":"Elo","bas":1482,"haut":1528,"votes":1165,"voisins":["elevenlabs-turbo-v2-5","inworld-tts-1-5-max"],"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":"Flash v2.5","tts_arena":"Eleven Flash v2.5"}}