Intel / article

Qwen2.5 Omni: See, Hear, Talk, Write, Do It All!

Source: qwenlm.github.io
Date: Jul 21, 2026

Why it matters

Announces Qwen2.5-Omni-7B, an end-to-end multimodal flagship model
Handles text, image, audio, and video inputs together
Delivers real-time streaming text and natural speech output

Key quotes

“We release Qwen2.5-Omni, the new flagship end-to-end multimodal model in the Qwen series.”

Transcript

QWEN CHAT HUGGING FACE MODELSCOPE DASHSCOPE GITHUB PAPER DEMO DISCORD We release Qwen2.5-Omni, the new flagship end-to-end multimodal model in the Qwen series. Designed for comprehensive multimodal perception, it seamlessly processes diverse inputs including text, images, audio, and video, while delivering real-time streaming responses through both text generation and natural speech synthesis. To try the latest model, feel free to visit Qwen Chat and choose Qwen2.5-Omni-7B. The model is now openly available on Hugging Face, ModelScope, DashScope,and GitHub, with technical documentation available in our Paper.

Read the source ↗qwenlm.github.io