QwenAudioAutomation & workflows
Qwen Audio Agent
qwen-audio-agent
A real-time voice runtime for AI Agents that supports full-duplex interaction while executing background tasks without interrupting the conversation.
- Operations
- Automation
- AI coding
- Desktop
- CLI
- Web
- Windows
- macOS
- Linux
- Self-hostable
- Runs locally
- Needs API key
- Popularity
- 2.2k Stars
- GitHub stars
- Recent activity
- 8/21/2026
- Updated in the last 30 days
- License
- APACHE-2.0
- Permissive
Why it matters
We look beyond stars: what problem it solves, whether it creates real utility, and what makes its approach worth noticing.
Problem
Addresses the issue of voice interaction interruptions or latency when AI assistants perform background tasks or tool calls, maintaining conversational continuity.
Practical value
Provides cross-platform desktop floating orbs (macOS/Windows/Linux), terminal TUI, and WebUI, supporting multiple backend Agent integrations with real-time task progress reporting.
Innovation / differentiation
Utilizes a decoupled architecture separating the real-time voice frontend from the asynchronous task execution backend, allowing users to continue conversing with the assistant while tasks are running.
Leverage potential
Supports integration with various mainstream coding Agents (e.g., Qwen Code, Kimi Code, Claude Code), allowing users to switch backend models based on their needs.
Why now
With the growing demand for real-time voice interaction and autonomous Agent task execution, this project integrates various Agent capabilities through a unified ACP architecture, aligning with current AI Agent development trends.
Community activity
In the last 90 days there were 21 new issues and 146 pull requests; the bounded issue/PR samples include 12 issue authors and 19 PR contributors, with 27 releases.
Maintainer responsiveness
The 21-issue window sample had a 67% close rate, and the 100-pull-request sample had a 80% merge rate. Maintainer-response observations covered 100% of that issue sample, with a 48% response rate and median first response of 7.5 hours.
Key highlights
- Supports full-duplex real-time voice interaction with natural interruption
- Runs frontend conversations and background tasks in parallel with live progress tracking
- Includes built-in computer-use capabilities for autonomous backend task execution
Quick start
How it is installed, how hard it is, and where to start.
Where it runs
Runs locally
Difficulty
Medium — some setup needed
- 01Install Qwen Audio Agent globally using npm.
- 02Run the configuration command and provide your DashScope API Key.
- 03Start the gateway service, then launch the TUI or WebUI in a separate terminal.
Best for
- Teams that want data on their own servers
- Developers who want to try it on their machine
More about it
Qwen Audio Agent is a real-time voice runtime designed to prevent conversation stalls during complex AI tasks. By separating the voice frontend from the backend task executor, it ensures the assistant remains present and responsive while performing code execution, tool calls, or long-running operations.
The project supports various backend Agents and offers multiple interfaces, including WebUI, terminal TUI, and a desktop floating orb. Users can configure persistent memory and leverage built-in computer-use capabilities for automated workflows.
Sources
Each field shows its status and source — expand to review.
11 · Expand
Sources
Each field shows its status and source — expand to review.
capability tags
Verifiedautomation, ai_coding
Source: admin_cms · cms editor · 8/18/2026
Latest release
Verifiedv1.11.0
Source: GitHub API · latest_release=v1.11.0 · 8/22/2026
License
VerifiedApache-2.0
Source: GitHub API · license.spdx_id=Apache-2.0 · 8/22/2026
needs api key
VerifiedYes
Source: admin_cms · cms editor · 8/13/2026
One-liner
Verified{"en":"A real-time voice runtime for AI Agents that supports full-duplex interaction while executing background tasks without interrupting the conversation.","zh":"一个支持全双工实时语音交互的 AI Agent 运行时，可在后台异步执行任务并保持对话连贯。"}
Source: admin_cms · cms editor · 8/13/2026
Platforms
Verifiedwindows, macos, linux
Source: admin_cms · cms editor · 8/13/2026
Category hint
Inferred from materialsai-apps
Source: Project README · hint=ai-apps · 8/13/2026
product forms
Verifieddesktop, cli, web
Source: admin_cms · cms editor · 8/18/2026
role tags
Verifiedoperations
Source: admin_cms · cms editor · 8/18/2026
supports local
VerifiedYes
Source: admin_cms · cms editor · 8/13/2026
supports self host
VerifiedYes
Source: admin_cms · cms editor · 8/13/2026
Related projects
Other verified projects matched by category, capabilities, and intended roles.
woodpecker
A self-hosted, plugin-extensible CI/CD engine with SQLite available by default for the server and a focused pipeline workflow.
Rundeck
A self-hosted runbook automation service with web, CLI, and API interfaces for turning operational procedures into repeatable jobs.
wechatauto-replica
An automation library for WeChat 4.x Windows client, enabling message reading, history export, and automated sending via local database decryption and hybrid UI drivers.
agent-device
Mobile app automation and verification for AI coding agents, enabling live interaction and testing across iOS, Android, HarmonyOS, and more.
hh-ai-agent
Job-search agent that finds HH.ru vacancies, evaluates them with an LLM, generates cover letters, and sends suitable matches to Telegram.
marketing-studio
An agent-driven marketing studio for Claude Code that generates product demos, logo reveals, launch videos, and social assets from a single command.