{"id":"alibaba-qwen3-omni-30b-a3b-instruct","nom":"Qwen3-Omni-30B-A3B-Instruct","editeur":"Alibaba","pays":"Chine","poids_ouverts":true,"poids_selon":null,"licence":"Apache 2.0","licence_selon":null,"liens":{"page":"https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Instruct","essayer":"https://huggingface.co/spaces/Qwen/Qwen3-Omni-Demo"},"fiche_auto":true,"page":"https://quelleia.com/voix/modeles/alibaba-qwen3-omni-30b-a3b-instruct/","releve":"2026-10-19","en_bref":"15e sur 16 en prononciation du français.","presentation":"Modèle omnimodal à poids ouverts d'Alibaba (Qwen) qui comprend texte, images, audio et vidéo et répond en texte ou en voix naturelle, en streaming temps réel. Cette version Instruct repose sur une architecture MoE en deux parties, Thinker et Talker.","sortie":"2025-09-22","langues":{"annoncees":{"annoncees":"10 langues en sortie vocale (19 en entrée vocale, 119 en texte), dont le français","nombre":10,"francais":true,"liste":["en","zh","fr","de","ru","it","es","pt","ja","ko"]},"prises_en_charge_selon_open_tts":null,"evaluees":["fr"]},"preuves":[{"appuie":["presentation"],"lu":"https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Instruct/raw/main/README.md (« It processes text, images, audio, and video, and delivers real-time streaming responses in both text and natural speech. »), 17/10/2026"},{"appuie":["presentation"],"lu":"https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Instruct/raw/main/README.md (« MoE-based Thinker-Talker design with AuT pretraining for strong general representations »), 17/10/2026"},{"appuie":["langues"],"lu":"https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Instruct/raw/main/README.md (« Supports 119 text languages, 19 speech input languages, and 10 speech output languages. »), 17/10/2026"},{"appuie":["langues"],"lu":"https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Instruct/raw/main/README.md (« English, Chinese, French, German, Russian, Italian, Spanish, Portuguese, Japanese, Korean. »), 17/10/2026"},{"appuie":["sortie"],"lu":"https://raw.githubusercontent.com/QwenLM/Qwen3-Omni/main/README.md (« 2025.09.22: 🎉🎉🎉 We have released [Qwen3-Omni] »), 17/10/2026"}],"classements":[{"id":"synthese/prononciation","nom":"Prononciation du français","rang":15,"sur":16,"valeur":14.23,"unite":"%","chiffres":{"rtfx":9.64,"taille_milliards":35.26,"clonage":false},"voisins":["voxtral-tts","resemble-ai-chatterbox"],"source":{"nom":"Open TTS Leaderboard","mention":"Source : Open TTS Leaderboard, Hugging Face","url":"https://huggingface.co/spaces/hf-audio/open_tts_leaderboard","releve":"2026-10-19"}}],"noms_dans_les_sources":{"hf_audio":"Qwen/Qwen3-Omni-30B-A3B-Instruct"}}