Qwen-Audio-3.1-ASR (Flash)
Speech and audio
qwen-audio-3.1-asr-flash-streaming
Price not published
Qwen-Audio-3.1-Realtime (Plus)
Alibaba’s hosted real-time voice agent model (WebSocket Realtime API, OpenAI-Realtime-style events).
Model idqwen-audio-3.1-realtime-plus
Price$0.80 text in, $6.40 text out per 1M tokens
Checked29 September 2026
Where it stands
16newer speech and audio models since its release
- NVIDIA Nemotron 3.5 Transcribe (30B-A4B)28 Oct 2026
- Hy-SimulMT-30B-A3B22 Oct 2026
- Eleven Realtime v1 Max / Mini20 Oct 2026
- Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)20 Oct 2026
- Voxtral Small Transcribe 320 Oct 2026
The 5 newest are listed. All speech and audio models
- Before it from Alibaba
- Qwen-Audio-3.1-TTS-Next22 Sep 2026
- Weights
- Closed weights; access is hosted only.
How to call it
2 ways to use Qwen-Audio-3.1-Realtime (Plus), with the model id each provider expects.
| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| QwenCloud (Realtime WebSocket) | qwen-audio-3.1-realtime-plus |
wss://maas.qwencloudapi.com/api-ws/v1/realtime?model=qwen-audio-3.1-realtime-plus |
qwencloud.com |
| Alibaba Cloud Model Studio (Singapore / Beijing) | qwen-audio-3.1-realtime-plus |
wss://{WorkspaceId}.sg-singapore.maas.aliyuncs.com/api-ws/v1/realtime |
help.aliyun.com |
Pricing
| Audio input | $6.40 per 1M tokens |
|---|---|
| Text input | $0.80 per 1M tokens |
| Text output | $6.40 per 1M tokens |
| Audio output | $24 per 1M tokens |
As published: “USD per 1M tokens (QwenCloud list price; audio/text output $24 when audio is generated, $6.40 text-only)”.
Source: qwencloud.com, checked 29 September 2026.
Specs
- Input
- Audio and text
- Output
- Audio and text
- Context window
- 262,144 tokens
- Max output
- 16,384 tokens
- Open weights
- No
- Licence
- Proprietary
- Released
- 23 September 2026
- Status
- Current
- Type
- Speech and audio
What stands out
What its maker marketed at launch, and what people found later, each with its source.
Full-duplex agentic voice (“Think, Act, Speak and Coordinate”)
Listens while speaking, decides whether to keep listening, speak, stop or resume; function calling and built-in web search. Task success 82.0% vs 78.4% for the previous version; replies to background speech fell from 73.0% to 13.0% (Full-Duplex-Bench v1.5).
Three turn-taking modes and voice cloning
server_vad, semantic smart_turn and push-to-talk modes; system voices plus cloned custom voices; 16 kHz PCM in, 24 kHz PCM out.
~85% price cut at launch
Alibaba cut Realtime prices about 85% with the 3.1 release (TTS ~70%, ASR up to 95%).
Notes
Languages: de, en, es, fr, id, it, ja, ko, pt, ru, zh (Mandarin, Cantonese and 18+ Chinese varieties). Predecessors qwen-audio-3.0-realtime-plus / -flash (July 2026) still listed.
Sources: https://www.qwencloud.com/models/qwen-audio-3.1-realtime-plus · https://help.aliyun.com/en/model-studio/qwen-audio-realtime-user-guides · https://arxiv.org/abs/2609.25176
Not yet checked against an official source: Press (MarkTechPost) reports interruption-stop latency 1.116 s vs 0.383 s for GPT-Realtime-2 and higher red-team refusal for GPT-Realtime-2; not verified on an official page. Release date is the announcement date (Qwen X post / Apsara); Model Studio pricing for this id not verified.