Qwen-Audio 3.0 Realtime Flash
Model overview
qwen-audio-3.0-realtime-flash
Qwen-Audio 3.0 Realtime Flash is a real-time speech model for real-time speech handling and duplex conversation, with parallel inference and omnidirectional streaming used to control end-to-end response latency.
multimodalaudiospeechrealtimevoice assistantrealtime voiceenterprise access
Representative version
qwen-audio-3.0-realtime-flash
| Company | Alibaba / Qwen |
|---|---|
| Release | 2026-07-14 |
| Release type | Model release |
| Parameters | Not disclosed |
| Architecture | Not disclosed |
| Context | Not disclosed |
| Input modalities | text / audio |
| Output modalities | text / audio |
| Tool use / function calling | Confirmed: Tool use, Function calling |
| Structured output / reasoning | Not shown: Reasoning |
| Vision / audio / video | Confirmed: Audio |
| Open weights / License | Weight status not disclosed / license not disclosed alibaba-qwen-qwen-audio-3-0-realtime-flash-current · License source pending verification |
| Vendor API | Available Qwen-Audio Realtime API guide - Alibaba Cloud Model Studioalibaba-qwen-qwen-audio-3-0-realtime-flash-current · 2026-07-14 |
| OpenRouter | Not separately listed on OpenRouter |
| Pricing | Official · checked 2026-07-20 · China mainland (Beijing): text input $0.413 · audio input $4.126 · text output $4.126 · audio output $13.752 · per 1M tokens |
| Benchmark | No reliable public source |
| Public signals | No reliable public source |
| Use cases | Low-latency voice assistants / Duplex customer service / Tool-using voice agents / voice assistant |
| Claim evidence | Release eventAlibaba Cloud Model Studio model lifecycle and updatesqwen-audio-3.0-realtime-flash · 2026-07-14 Model specificationsQwen-Audio real-time voice model - Alibaba Cloud Model StudioQwen-Audio 3.0 Realtime Flash · qwen-audio-3.0-realtime-flash |
OpenRouter
Pricing / context / availability
| OpenRouter | Not separately listed on OpenRouter |
|---|---|
| OpenRouter listing | Not separately listed in the current OpenRouter public list |
| Mapped version | qwen-audio-3.0-realtime-flash alibaba-qwen-qwen-audio-3-0-realtime-flash-current |
| Pricing | Official · checked 2026-07-20 · China mainland (Beijing): text input $0.413 · audio input $4.126 · text output $4.126 · audio output $13.752 · per 1M tokens |
| Context | Not disclosed |
| Speed/Latency | No reliable public source |
| Snapshot time | 2026-08-11T06:28:09.895Z |
| Source | View source |
Verified limitations
Usage boundaries
- Beijing region only; 50 turns or 300 seconds is the audio-history window, not a token context limit.
- Function calling is supported; reasoning mode is not.
Missing public information
Public information not yet available
Parameter scale not disclosedNot listed on OpenRouterNo reliable benchmark sourceNo public model-card activity countersNo linkable model-specific reviewSpeed/latency not disclosed