Skip to main content
Realtime API

Realtime API overview

The Realtime API provides multiple transport protocols, each optimized for different requirements such as performance, latency, weak-network resilience, and integration cost

The Realtime API provides multiple transport protocols, each optimized for different requirements such as performance, latency, weak-network resilience, and integration cost. The Realtime API supports three transport protocols: AOQ (AI over QUIC), WebRTC, and WebSocket. Choose the protocol that best fits your business scenario.
DimensionAOQWebRTCWebSocket
Use casesAI multimodal real-time interaction, weak-network conditions, mixed data transmissionBrowser-based interaction, traditional audio and video callsServer-side integration, rapid prototyping
Browser compatibilityNot supportedNatively supportedNatively supported
Integration difficultyLowMediumMinimal
Weak-network resilienceExcellentGoodPoor
Data typesAudio/video + textAudio/video + textText/audio/image
Connection setup speedFastSlowSlow
Echo cancellation and noise suppressionBuilt-inBuilt-inNone; the client must handle them
AI scenario fitPurpose-built for AI multimodal data characteristicsTraditional design; requires extra adaptation for AI scenariosBasic; suitable for text-only scenarios or scenarios with low real-time requirements
Client platform supportAndroid / iOS / HarmonyOSBrowsers, mobile clientsAll platforms (any environment that supports WebSocket)
Select a protocol based on your requirements:
  • AOQ: Best for AI real-time interaction scenarios with the most demanding requirements for latency, weak-network resilience, and multimodal data transmission, especially native mobile apps. Echo cancellation and noise suppression are built in.
  • WebRTC: Best for traditional audio and video call scenarios that require native browser support or already run on WebRTC infrastructure. Echo cancellation and noise suppression are built in.
  • WebSocket: Best for server-side integration, rapid prototyping, and scenarios that require a minimal integration barrier. Use the DashScope SDK to quickly implement real-time voice conversation.

Supported models and applications

The following table shows how each protocol supports different models and applications:
Model/application typeModelAOQWebRTCWebSocket
Real-time omniqwen3.5-omni-plus-realtimeSupportedSupportedSupported
Real-time omniqwen3.5-omni-flash-realtimeSupportedSupportedSupported
Real-time audio translationqwen3.5-livetranslate-flash-realtimeSupportedSupportedSupported
Real-time speech recognitionQwen-Audio-3.0-ASR-Flash-Streaming, Fun-ASR-Realtime series modelsSupportedUnsupportedSupported
Real-time speech synthesisCosyVoice series modelsSupportedUnsupportedSupported
Real-time speech synthesisqwen-audio-3.0-tts-flash, qwen-audio-3.0-tts-plusSupportedUnsupportedSupported
Realtime Audio Chatqwen-audio-3.0-realtime-plus, qwen-audio-3.0-realtime-flashSupportedSupportedSupported
For information such as model names, context windows, prices, and snapshot versions, see the QwenCloud console. For rate limits, see Rate limiting.

Best practices