Qwen open-sources Qwen3-Omni
Qwen releases an open-weight, native end-to-end omni-modal model with real-time text and natural-speech output.
QW1 English report
MODEL
Qwen3-Omni
- Release date:
- 2025-09-22
- Parameters:
- 30B-A3B
- Input/output:
- Text + Image + Audio + Video → Text + Audio
- Interaction:
- Real-time
- Openness:
- Open-source
- Organization:
- Alibaba Cloud
Official links | Chat | Code Plan | Agent tools | API |
|---|---|---|---|---|
| Global | — | |||
| Mainland China |
Related English reports
English reports linked to this entity will appear here as their translations are published.
AI-generated · awaiting review