QwenAudio GitHub avatar

qwen-audio-agent

QwenAudio

Qwen Audio Agent is a full-duplex real-time voice interaction tool that connects to multiple backend agents for continuous conversational and parallel task handling.

Stars

18

7-day growth

No data

Forks

0

Open issues

9

License

Apache-2.0

Last updated

2026-07-28

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It enables persistent voice conversations with natural interruption, runs background tasks concurrently, and supports a wide range of backend agents (OpenCode, OpenClaw, etc.) with multiple frontends (TUI, WebUI, macOS desktop orb).

Who it is for

  • Developers building voice-enabled applications
  • Users who want a persistent personal assistant with task automation
  • Teams needing multi-agent orchestration for code and tool tasks
  • macOS users seeking a desktop voice floating ball interface

Use cases

  • Real-time voice chat with ability to interrupt and ask follow-up questions
  • Delegating background tasks (code, tool usage) while continuing front conversation
  • Managing user profiles and cross-session personal memory
  • Using a single gateway to interface with various agent protocols (ACP, native)

Strengths

  • Full-duplex audio with echo cancellation on macOS and optional full-duplex on other platforms
  • Seamless integration with multiple popular backend agents (OpenCode, OpenClaw, Qoder, etc.)
  • Parallel conversation and background task execution with progress query and cancellation
  • Local user profile and long-term memory stored locally without cloud dependencies

Considerations

  • Requires Node.js 22.22.2+ or 24.15.0+ and a DashScope API Key from Alibaba Cloud
  • Linux and Windows default to half-duplex mode; full-duplex requires headphones to avoid echo
  • Full backend permission mode allows automatic command execution, recommended only in trusted projects

README quick start

安装

Description

A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents

Related repositories

Similar projects matched by category, topics, and programming language.

gnipbao
Featured
gnipbao GitHub avatar

story-to-handdrawn-video

A Remotion-based tool that converts Chinese story text or ordered hand-drawn images into vertical hand-drawn diary-comic animation with handwritten captions, left-to-right reveals, optional page-curl transitions, and silent H.264 output for post-production dubbing.

AI & Machine LearningAI Agents
683
makecindy
Featured
makecindy GitHub avatar

cindy

Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.

AI & Machine LearningLarge Language Models
958
mereyabdenbekuly-ctrl
Featured
mereyabdenbekuly-ctrl GitHub avatar

clodex-ide

Clodex is an open-source, local-first agentic IDE that combines persistent AI tasks, code, terminal, browser, Git, models, memory, and governed execution in one Electron workspace, currently in technical preview.

AI & Machine LearningAI Agents
859