#36 · Primary category： Foundation Models
Qwen3-Omni
Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.
Project last updated：04/23/26
GitHub Stars
4.0K
Forks
291
Contributors
1
License
Apache-2.0
Why we included this project
Most open models force you to combine separate speech, vision, and language components yourself. Qwen3-Omni instead ships as one end-to-end model from Alibaba Cloud's Qwen team that takes text, audio, images, and video as input and replies in real time with natural speech, which suits voice assistants and live transcription-and-response tools that cannot afford pipeline lag. The repo includes model weights on Hugging Face and ModelScope, inference code, cookbooks, and an online demo, so you can try the behavior interactively before integrating it. For a team that wants a working baseline for spoken and visual interaction without assembling several single-purpose models, this is a practical place to start.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
MiniCPM-V
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
generative-models
Generative Models by Stability AI
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities