As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/qwen-audio-3-1-realtime/

# Qwen-Audio-3.1-Realtime (Plus)

Alibaba (Qwen), Qwen-Audio 3.1 family. Status: current. Type: speech and audio. Released: 2026-09-23.

## How to call it

| 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 | https://www.qwencloud.com/models/qwen-audio-3.1-realtime-plus |
| Alibaba Cloud Model Studio (Singapore / Beijing) | `qwen-audio-3.1-realtime-plus` | wss://{WorkspaceId}.sg-singapore.maas.aliyuncs.com/api-ws/v1/realtime | https://help.aliyun.com/en/model-studio/qwen-audio-realtime-user-guides |

## 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
- Unit as published: USD per 1M tokens (QwenCloud list price; audio/text output $24 when audio is generated, $6.40 text-only)
- Source: https://www.qwencloud.com/models/qwen-audio-3.1-realtime-plus
- Last checked: 2026-09-29

## Specs

- Input: audio, text
- Output: audio, text
- Context window: 262,144 tokens
- Max output: 16,384 tokens
- Open weights: no
- Licence: proprietary

## Where it stands

- Newer speech and audio models in the registry since its release: 16. The 5 newest:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
  - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/
  - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/
  - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/
  - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/
- Before it from Alibaba: Qwen-Audio-3.1-TTS-Next (2026-09-22) https://postcutoff.com/m/qwen-audio-3-1-tts-next/
- Closed weights; access is hosted only.

## What stands out

- 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). Source: https://arxiv.org/abs/2609.25176
- 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. Source: https://help.aliyun.com/en/model-studio/qwen-audio-realtime-user-guides
- ~85% price cut at launch: Alibaba cut Realtime prices about 85% with the 3.1 release (TTS ~70%, ASR up to 95%). Source: https://x.com/Alibaba_Qwen/status/2102687258990026993

## 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. 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.

Alibaba's hosted real-time voice agent model (WebSocket Realtime API, OpenAI-Realtime-style events).

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

Model page: https://postcutoff.com/m/qwen-audio-3-1-realtime/