Real-time voice conversation
Qwen-Audio-Realtime is designed for real-time voice conversations. The models accept text and streaming audio and can return text and audio.
qwen-audio-3.1-realtime-plus, qwen-audio-3.1-realtime-flash, qwen-audio-3.0-realtime-plus, and qwen-audio-3.0-realtime-flash support WebSocket, WebRTC, and AOQ.
Protocol selection
For general guidance, see Choose an access method. See the access and event references for the inputs, outputs, and event fields available for your model.
-
With WebSocket, send and receive audio and text in events.
Browsers natively support WebSocket. Follow the model's authentication requirements and keep long-term API keys on the server.
-
With WebRTC, use audio tracks for speech and the DataChannel for text and model events.
-
With AOQ (AI over QUIC), use the client SDK to transmit audio and a separate Data track for text and model events.
The client SDK is available for Android, iOS, HarmonyOS, Windows, macOS, Electron, and Linux. The AOQ access guide links to SDK downloads and platform-specific API references.
All three protocols can be used for Token Plan. Available models and regions are subject to the specifications outlined in Token Plan Personal Edition and Team Edition.