qwen-audio-agent

Real-time voice runtime enabling AI agents to continuously communicate, work, and remain present.

🇨🇳 DomesticFreeOpen sourceGeneral开源桌面操作全双工语音交互

Platforms: WebDesktopAPI

Region: Domestic
Pricing: Free
Open source: Yes
GitHub Stars: ★ 1.1k
Source: GitHub
Added: 2026-08-02
Last verified: 2026-08-02
GitHub: github.com/QwenAudio/qwen-audio-agent

Overview

Qwen Audio Agent is a real-time voice runtime designed to maintain continuous conversation and task processing for AI agents. Whether chatting, thinking, or handling tasks, the agent stays available and responds naturally. It supports full-duplex real-time voice interaction, natural interruptions, multi-turn conversations, and can integrate with various backend agents to enable concurrent front-end dialogue and back-end task execution. Ideal for scenarios requiring sustained dialogue and task management.

Key features

▪Full-duplex real-time voice interaction
▪Supports natural interruptions and multi-turn conversations
▪Concurrent front-end dialogue and back-end task execution
▪Supports integration with multiple backend agents

Use cases

Customer service with continuous conversationPersonal assistant for multitaskingReal-time translation in remote meetingsInteractive assistant in educational settings