{"id":"coqui-xtts-v2","nom":"XTTS v2","editeur":"Coqui","pays":null,"poids_ouverts":true,"poids_selon":null,"licence":"Coqui Public Model License","licence_selon":null,"liens":{"page":"https://huggingface.co/coqui/XTTS-v2"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/coqui-xtts-v2/","releve":"2026-10-19","en_bref":"27e sur 31 en synthèse vocale en français, dans un peloton de 3 modèles que la marge d'erreur ne permet pas de séparer ; 88e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un peloton de 6 modèles que la marge d'erreur ne permet pas de séparer.","presentation":"Modèle de génération de voix qui clone une voix dans d'autres langues à partir d'un extrait de 6 secondes, avec transfert d'émotion et de style. Par rapport à XTTS v1, il ajoute le hongrois et le coréen, accepte plusieurs voix de référence et améliore la prosodie.","sortie":"2023-11-06","langues":{"annoncees":{"annoncees":"17 langues, dont le français","nombre":17,"francais":true,"liste":["en","es","fr","de","it","pt","pl","tr","ru","nl","cs","ar","zh","ja","hu","ko","hi"]},"prises_en_charge_selon_open_tts":null,"evaluees":["fr","en"]},"preuves":[{"appuie":["presentation"],"lu":"https://huggingface.co/coqui/XTTS-v2/raw/main/README.md (« ⓍTTS is a Voice generation model that lets you clone voices into different languages by using just a quick 6-second audio clip. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/coqui/XTTS-v2/raw/main/README.md (« Emotion and style transfer by cloning. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/coqui/XTTS-v2/raw/main/README.md (« 2 new languages; Hungarian and Korean - Architectural improvements for speaker conditioning. - Enables the use of multiple speaker references and interpolation between speakers. »), 17/10/2026"},{"appuie":["langues"],"lu":"https://huggingface.co/coqui/XTTS-v2/raw/main/README.md (« XTTS-v2 supports 17 languages: **English (en), Spanish (es), French (fr), German (de), Italian (it), Portuguese (pt), »), 17/10/2026"},{"appuie":["langues"],"lu":"https://huggingface.co/coqui/XTTS-v2/raw/main/README.md (« Polish (pl), Turkish (tr), Russian (ru), Dutch (nl), Czech (cs), Arabic (ar), Chinese (zh-cn), Japanese (ja), Hungarian (hu), Korean (ko) Hindi (hi)**. »), 17/10/2026"},{"appuie":["sortie"],"lu":"https://api.github.com/repos/coqui-ai/TTS/releases/tags/v0.20.0 (« XTTS v2.0 by @Edresson in https://github.com/coqui-ai/TTS/pull/3137 »), 17/10/2026"}],"classements":[{"id":"synthese/francais","nom":"Synthèse vocale en français","rang":27,"sur":31,"valeur":1013.28,"unite":"Elo","bas":991.28,"haut":1035.28,"votes":1175,"chiffres":{"prix_par_million_caracteres":40.44,"date_sortie":"2023-11-08"},"voisins":["fish-audio-s2-pro","openaudio-s1"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/xtts","releve":"2026-10-19"}},{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":88,"sur":96,"valeur":916.59,"unite":"Elo","bas":901.59,"haut":931.59,"votes":2611,"chiffres":{"prix_par_million_caracteres":40.44,"date_sortie":"2023-11-08"},"voisins":["google-wavenet","rime-mist-v2"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/xtts","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"XTTS v2"}}