{"id":"openvoice-v2","nom":"OpenVoice v2","editeur":"MyShell","pays":"Singapour","poids_ouverts":true,"poids_selon":null,"licence":"MIT","licence_selon":null,"liens":{"page":"https://research.myshell.ai/open-voice","essayer":"https://huggingface.co/spaces/myshell-ai/OpenVoiceV2"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/openvoice-v2/","releve":"2026-10-19","en_bref":"31e sur 31 en synthèse vocale en français ; 81e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un groupe de 6 modèles trop proches pour être départagés.","presentation":"Modèle de clonage de voix instantané qui reproduit le timbre d'un locuteur à partir d'un court extrait et permet de régler l'émotion, l'accent, le rythme, les pauses et l'intonation. La version 2 améliore la qualité audio et prend en charge nativement six langues, et le clonage fonctionne aussi vers des langues absentes des données d'entraînement.","sortie":"2024-04","langues":{"annoncees":{"annoncees":"6 langues, dont le français","nombre":6,"francais":true,"liste":["en","es","fr","zh","ja","ko"]},"prises_en_charge_selon_open_tts":null,"evaluees":["fr","en"]},"preuves":[{"appuie":["presentation"],"lu":"https://research.myshell.ai/open-voice (« We introduce OpenVoice, a versatile instant voice cloning approach that requires only a short audio clip from the reference speaker to replicate their voice and generate speech in multiple languages. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/myshell-ai/OpenVoiceV2/raw/main/README.md (« OpenVoice enables granular control over voice styles, such as emotion and accent, as well as other style parameters including rhythm, pauses, and intonation. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/myshell-ai/OpenVoiceV2/raw/main/README.md (« Neither of the language of the generated speech nor the language of the reference speech needs to be presented in the massive-speaker multi-lingual training dataset. »), 17/10/2026"},{"appuie":["presentation","sortie"],"lu":"https://huggingface.co/myshell-ai/OpenVoiceV2/raw/main/README.md (« In April 2024, we release OpenVoice V2, which includes all features in V1 and has: 1. Better Audio Quality. »), 17/10/2026"},{"appuie":["langues","presentation"],"lu":"https://huggingface.co/myshell-ai/OpenVoiceV2/raw/main/README.md (« English, Spanish, French, Chinese, Japanese and Korean are natively supported in OpenVoice V2. »), 17/10/2026"}],"classements":[{"id":"synthese/francais","nom":"Synthèse vocale en français","rang":31,"sur":31,"valeur":782.1,"unite":"Elo","bas":752.1,"haut":812.1,"votes":1181,"chiffres":{"prix_par_million_caracteres":8.33,"date_sortie":"2024-04-01"},"voisins":["nvidia-magpie-tts-zeroshot"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/openvoice","releve":"2026-10-19"}},{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":81,"sur":96,"valeur":956.6,"unite":"Elo","bas":943.6,"haut":969.6,"votes":3042,"chiffres":{"prix_par_million_caracteres":8.33,"date_sortie":"2024-04-01"},"voisins":["murf-speech-gen-2","microsoft-vibevoice-1-5b"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/openvoice","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"OpenVoice v2"}}