Model · multimodal model
Qwen-Audio-3.1-Realtime
Qwen-Audio-3.1-Realtime is a multimodal model from Alibaba Qwen, first covered on 29 September 2026. It is available through an API. Its context window is 262K tokens (245K input, 16K output).
Last updated
At a glance
- Made by
- Alibaba Qwen
- Type
- Multimodal model
- Availability
- API
- Licence
- Not stated
- Context window
- 262K tokens (245K input, 16K output)
- First seen
- 29 September 2026
Taken from the coverage, not from our own testing; "not stated" means none of the reports we read gave it. All tracked models →
1 story about Qwen-Audio-3.1-Realtime
-
Alibaba releases Qwen-Audio-3.1-Realtime for voice agents at 85% lower prices
Alibaba’s Qwen team launched Qwen-Audio-3.1-Realtime, a full-duplex speech model designed for voice agents that can reason, call tools, and manage turn-taking in real-time conversations. The model is part of a…
1 sourceMarkTechPost
