{"id":"alibaba-qwen-audio-3-0-tts-plus","nom":"Qwen-Audio-3.0-TTS-Plus","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/qwen-audio-3-0-tts-plus","essayer":"https://www.alibabacloud.com/help/en/model-studio/text-to-speech"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/alibaba-qwen-audio-3-0-tts-plus/","releve":"2026-10-19","en_bref":"12e sur 31 en synthèse vocale en français, dans un groupe de 4 modèles trop proches pour être départagés ; 6e sur 96 en synthèse vocale en anglais (Artificial Analysis), ex æquo avec 4 autres modèles dont les marges d'erreur se recouvrent.","presentation":"Modèle de synthèse vocale d'Alibaba orienté qualité, servi par l'API Model Studio, dont l'émotion, le ton, le débit et le style se règlent par instructions libres et par balises. Alibaba le destine aux livres audio, au doublage et aux voix de marque, et annonce un meilleur rendu des dialectes chinois et des langues peu dotées.","sortie":"2026-07-14","langues":{"annoncees":{"annoncees":"16 langues en voix clonée, dont le français (voix système en chinois et en anglais)","nombre":16,"francais":true,"liste":["zh","en","ja","ko","ru","fr","de","pt","th","id","vi","es","it","ms","fil","ar"]},"prises_en_charge_selon_open_tts":null,"evaluees":["fr","en"]},"preuves":[{"appuie":["presentation"],"lu":"https://www.alibabacloud.com/help/en/model-studio/qwen-audio-3-0-tts-plus (« Qwen-Audio-3.0-TTS-Plus is a high-performance speech synthesis model, designed for high-quality speech generation scenarios. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://www.alibabacloud.com/help/en/model-studio/qwen-audio-3-0-tts-plus (« Compared with the previous version, it supports more low-resource languages and Chinese dialects, significantly improves dialect authenticity »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://www.alibabacloud.com/help/en/model-studio/qwen-audio-3-0-tts-plus (« such as content creation, audiobooks, film and video dubbing, brand voice design, and premium speech services »), 17/10/2026"},{"appuie":["sortie"],"lu":"https://www.alibabacloud.com/help/en/model-studio/newly-released-models (« Speech synthesis, Realtime speech synthesis 2026-07-14 International qwen-audio-3.0-tts-plus »), 17/10/2026"},{"appuie":["langues"],"lu":"https://www.alibabacloud.com/help/en/model-studio/tts-model (« qwen-audio-3.0-tts-flash WebSocket Supported Unsupported Supported Supported languages : System voices (varies by voice): Chinese (Mandarin), English Cloned voices »), 17/10/2026"},{"appuie":["langues"],"lu":"https://www.alibabacloud.com/help/en/model-studio/tts-model (« English, Japanese, Korean, Russian, French, German, Portuguese, Thai, Indonesian, Vietnamese, Spanish, Italian, Malaysian, Filipino, and Arabic CosyVoice »), 17/10/2026"}],"classements":[{"id":"synthese/francais","nom":"Synthèse vocale en français","rang":12,"sur":31,"valeur":1166.31,"unite":"Elo","bas":1143.31,"haut":1189.31,"votes":668,"chiffres":{"prix_par_million_caracteres":19.31,"date_sortie":"2026-09-15"},"voisins":["google-gemini-3-8-flash-lite-tts","elevenlabs-multilingual-v2"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/cosyvoice-tts","releve":"2026-10-19"}},{"id":"synthese/artificial-analysis","nom":"Synthèse vocale en anglais, Artificial Analysis","rang":6,"sur":96,"valeur":1264.57,"unite":"Elo","bas":1250.57,"haut":1278.57,"votes":2264,"chiffres":{"prix_par_million_caracteres":19.31,"date_sortie":"2026-09-15"},"voisins":["google-gemini-3-8-flash-tts","inworld-realtime-tts-2"],"source":{"nom":"Artificial Analysis","mention":"Source : Artificial Analysis","url":"https://artificialanalysis.ai/text-to-speech/model-families/cosyvoice-tts","releve":"2026-10-19"}}],"noms_dans_les_sources":{"artificial_analysis":"Qwen-Audio-3.0-TTS-Plus"}}