{"id":"alibaba-qwen3-tts-flash","nom":"Qwen3 TTS Flash","editeur":"Alibaba","pays":"Chine","poids_ouverts":false,"poids_selon":"Artificial Analysis","licence":null,"licence_selon":null,"liens":{"page":"https://www.alibabacloud.com/help/en/model-studio/tts-model","essayer":"https://www.alibabacloud.com/help/en/model-studio/qwen-tts"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/alibaba-qwen3-tts-flash/","releve":"2026-10-19","en_bref":"84e sur 96 en synthèse vocale en anglais (Artificial Analysis), dans un groupe de 6 modèles trop proches pour être départagés.","presentation":"Modèle de synthèse vocale d'Alibaba servi par l'API Model Studio, avec 17 voix expressives et une synthèse à faible latence. Il garde les mêmes caractéristiques de voix d'une langue à l'autre et prend en charge plusieurs dialectes chinois.","sortie":"2025-09-16","langues":{"annoncees":{"annoncees":"10 langues, dont le français","nombre":10,"francais":true,"liste":["zh","en","de","it","pt","es","ja","ko","fr","ru"]},"prises_en_charge_selon_open_tts":null,"evaluees":["en"]},"preuves":[{"appuie":["presentation"],"lu":"https://www.alibabacloud.com/help/en/model-studio/newly-released-models (« The Qwen3-TTS-Flash is Tongyi's latest offline text-to-speech foundation model, featuring 17 expressive voices while enabling low-latency, high-stability audio synthesis. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://www.alibabacloud.com/help/en/model-studio/newly-released-models (« It supports multilingual and dialect outputs with consistent voice characteristics across languages. »), 17/10/2026"},{"appuie":["sortie"],"lu":"https://www.alibabacloud.com/help/en/model-studio/newly-released-models (« Speech synthesis 2025-09-16 International qwen3-tts-flash-2025-09-18 »), 17/10/2026"},{"appuie":["langues"],"lu":"https://www.alibabacloud.com/help/en/model-studio/tts-model (« Qwen3-TTS-Flash series (system voices) ( qwen3-tts-flash , qwen3-tts-flash-realtime ): Chinese (Mandarin, Beijing, Shanghainese, Sichuan, Nanjing, Shaanxi, Hokkien, Tianjin, Cantonese »), 17/10/2026"},{"appuie":["langues"],"lu":"https://www.alibabacloud.com/help/en/model-studio/tts-model (« English, German, Italian, Portuguese, Spanish, Japanese, Korean, French, and Russian »), 17/10/2026"}],"classements":[{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":84,"sur":96,"valeur":941.86,"unite":"Elo","bas":927.86,"haut":955.86,"votes":2167,"chiffres":{"prix_par_million_caracteres":11.03,"date_sortie":"2025-09-22"},"voisins":["neuphonic-tts","alibaba-qwen3-tts"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/qwen","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"Qwen3 TTS Flash"}}