#496 · Primary category： AI Agents & Automation
qwen-audio-agent
A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents
Project last updated：08/29/26
GitHub Stars
2.3K
Forks
195
Contributors
22
License
Apache-2.0
Why we included this project
Most voice assistants stop listening the moment they start answering. This runtime is built for realtime, full-duplex conversation: the agent can be interrupted mid-task, keeps talking while it works, and reports back when the job finishes. It includes terminal, web, and desktop apps for macOS, Windows, and Linux, and pairs the Qwen Audio 3.0 realtime speech model with coding agents like OpenCode, Codex, and Claude Code that can call tools, run code, and operate the computer. That makes it a practical base for prototyping voice agents that need to do real work behind the conversation, or for reusing an existing agent setup instead of building a speech layer from scratch.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
hermes-agent
The agent that grows with you
n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
deepseek-harness
DeepSeek Harness: Everything is a Plugin.
AutoGPT
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.