Qwen-Audio-3.1-Realtime

Name: Qwen-Audio-3.1-Realtime
Author: Alibaba

AlibabaProprietaryPending Human Review

Qwen-Audio-3.1-Realtime is a proprietary language-capable speech conversation model for fluid real-time dialogue. It combines speech reasoning with duplex interaction, allowing conversational responses rather than only transcription or speech synthesis. The 3.1 Plus update supports a 262,144-token context, function calling, web search, voice cloning, and additional system voices, while retaining the 3.0 Plus integration protocol. Hosted streaming APIs provide access; no downloadable weights or checkpoint parameter count is verified.

2026-09-20

Detailed architecture not publicly disclosed

Proprietary

Compare with other models

Specifications

Architecture: Detailed architecture not publicly disclosed
License: Proprietary
Context Window: 262,144 tokens
Type: multimodal
Modalities: textaudio

Benchmark Scores

Advanced Specifications

Model Family: Qwen
API Access: Available
Chat Interface: Not Available
Variants: Qwen-Audio-3.1-Realtime-Plus

Capabilities & Limitations

Capabilities: speech conversationduplex dialogueaudio reasoning
Known Limitations: Requires the streaming service protocol and compatible audio handling.Conversation quality depends on audio conditions; speech-only ASR/TTS siblings have different scopes.
Notable Use Cases: voice assistantsinteractive spoken customer supportreal-time dialogue research
Function Calling Support: Yes
Tool Use Support: Yes

Resources

docs.qwencloud.com/changelog/models

Related Models

IndustryLLM

Alibaba

IndustryLLM is Alibaba’s open-weight language model for industrial procurement and engineering-standard reasoning. It adapts Qwen3.5-35B-A3B-Base through continued pre-training on industrial documents and transactions followed by task-focused supervised fine-tuning. The 35.95B-parameter hybrid mixture-of-experts network activates approximately 3B per token. Training targets informal buyer language, ambiguous product codes, contradictory specifications, and evidence-based constraint evaluation. Apache-licensed BF16 weights are published. Its 262K architectural context is distinct from 12,288-token packed fine-tuning sequences; this record uses the supported training length conservatively. The September 25 paper predates later discovery-index coverage.

Typetext

Parameters35.95B total, approximately 3B active

2026-09-25

Open Weights

Details Compare

Qwen3.8-Omni-Flash

Alibaba

Qwen3.8-Omni-Flash is a native omnimodal agent model built on the Qwen3.8-Flash-Next architecture. It accepts text, images, audio, and video in a million-token context, extending coding, GUI operation, and knowledge work to audio-visual productivity. Standard APIs return text, while the subsequently available Realtime variant supports text and speech output, multichannel audio, video aggregation, and remote MCP tools. Hosted access and companion plugins support video editing, multimedia summarization, and real-time conversations; its weights are not publicly released.

Qwen3.8-LiveTranslate-Flash

Alibaba

Qwen3.8-LiveTranslate-Flash is a language-capable real-time interpretation model that uses speech and visual context to translate conversations. It recognizes 60 source languages and supports spoken output in 29 languages, with text and audio responses exposed through the Realtime API. Visual grounding helps resolve terminology and references during meetings, classes, and livestreams. This update improves latency and enables real-time speaker diarization and transcription by default; the September 17 API changelog precedes the following launch article. Weights are not publicly downloadable.