ϟDomestic Models MiniMax Releases M3.1 Flash: 3x Performance Boost, 70% Cost Reduction Learn MoreϟDomestic Models Kimi K3 Released and API Opened Read More →✦New Model Launch Wan3.0 Released View Now →✦New Model Launch DeepSeek V4.1 Flash: Native Multimodal, Outperforms V4 Pro with Lower API Pricing View Details✦New Model Online Seedance 2.5 Release Details View Now →ϟDomestic Models MiniMax Releases M3.1 Flash: 3x Performance Boost, 70% Cost Reduction Learn More
AGTCloud
Contact us Careers
Audioqwen-audio-3.0-realtime-flash
阿里巴巴 · Audio

Qwen-Audio-3.0-Realtime-Flashis a next-generation, real-time, full-duplex speech foundation model that has topped global authoritative benchmarks, ranking first overall in the "Speech-to-Speech" category on Artificial Analysis—a leading independent evaluation platform. This end-to-end model balances high-level intelligence with the natural pacing of full-duplex conversation, ensuring seamless, fluid real-time interaction without compromising speech reasoning capabilities. Through engineering optimizations such as parallel inference and omnidirectional streaming, it minimizes end-to-end response latency, delivering a conversational experience that is both fast and intelligent. The Flash Edition places greater emphasis on ultra-fast responsiveness.

Overview

Modalities
Context length40K
Max output8K

Pricing

Availability

Service statusPast 24 hours

Parameters

Model / versionqwen-audio-3.0-realtime-flash
Input modalitiesText / Audio
Output modalitiesText / Audio
Sampling parameters—
Context length40K
Max output8K

Example request

# WebSocket only. Send the frames below after connecting.
wscat -c 'wss://api.agtcloud.cn/v1/realtime?model=qwen-audio-3.0-realtime-flash' \
  -H 'Authorization: Bearer YOUR_API_KEY'
{"type":"conversation.item.create","item":{"type":"message","role":"user","content":[{"type":"input_text","text":"Hello!"}]}}
{"type":"response.create"}

Available endpoints

openai-realtimeWS /v1/realtime?model=qwen-audio-3.0-realtime-flashAPI reference

OpenAI Realtime API over WebSocket. The model is selected by the model query parameter.

EXPLORE MODELS

More Audio

Compare capabilities, context and price across models of the same type.

Browse all
小米

High-quality voice synthesis with precise adherence to style instructions. Supports inline emotion tags for word-level control and can capture a character’s vocal persona with zero-shot prompting.

Price · per call¥0
View model
阿里巴巴

Omni-modal model for text, vision, audio, and multimodal agent tasks

Input / Output · per 1M tokensFrom ¥2.2 / ¥13.3
View model
阿里巴巴

Omni-modal model for text, vision, audio, and multimodal agent tasks

Input / Output · per 1M tokensFrom ¥7 / ¥40
View model
阿里巴巴

qwen3.5-omni-flash-realtime is a model from Alibaba for real-time multimodal interaction.

Input / Output · per 1M tokensFrom ¥3.3 / ¥20
View model
阿里巴巴

qwen3.5-omni-plus-realtime is a model from Alibaba for real-time multimodal interaction.

Input / Output · per 1M tokensFrom ¥10 / ¥60
View model