Qwen-Audio-3.1-Realtime-Flash
Qwen-Audio-3.1-Realtime-Flash is a real-time duplex speech model that accepts and produces text and audio. It supports function calling, web search, voice cloning, and a 262,144-token context window.
What it does
Developers can use it to build real-time speech applications with voice cloning, web search, or function calling.
- Availability
- Listed under International
- Pricing model
- Not established
- Deployment
- Not established
- Privacy
- Not established
- Licence
- Not established
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
4 claims- The model supports real-time duplex speech with text and audio input and output. [1]
A real-time duplex speech model with text and audio input and output, function calling, web search, and voice cloning.
Alibaba Qwen. Quoted text is outside CC BY 4.0 and keeps its original rights. - It supports function calling, web search, and voice cloning. [1]
A real-time duplex speech model with text and audio input and output, function calling, web search, and voice cloning.
Alibaba Qwen. Quoted text is outside CC BY 4.0 and keeps its original rights. - Its context window is 262,144 tokens. [1]
The context window is 262,144 tokens.
Alibaba Qwen. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model is listed under International. [1]
Qwen3.8-Flash is the latest multimodal model from the Qwen family, combining powerful reasoning and generation with remarkable speed.
Alibaba Qwen. Quoted text is outside CC BY 4.0 and keeps its original rights.
Sources
1
1
Alibaba QwenOwner-controlled
https://www.alibabacloud.com/help/en/model-studio/newly-released-models#2026-10-27
Retrieved 2026-10-28 00:19 UTC
Verified
Versions
1| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 1 | 2026-10-28 00:20 UTC | publication | None | Current |
In briefs
1- New models bring live speech translation and voice features Daily brief 2026-10-28
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.