Skip to content
李旭 edited this page Aug 29, 2026 · 3 revisions

qwen-audio-agent Wiki

A realtime full-duplex voice runtime for AI coding agents — talk to Claude Code, Codex, OpenCode and more like a phone call.

What is qwen-audio-agent?

qwen-audio-agent is an open-source voice frontend for coding agents. It listens, understands, and speaks in real time, delegating deep work to your backend agent through the open ACP protocol — then announces results back into the conversation.

  • Full-duplex: speak while the agent works; interrupt anytime (barge-in)
  • Task delegation: quick questions answered instantly, deep tasks routed to the backend agent
  • Spoken results: long-running task outcomes are read back aloud
  • Local wake word: on-device wake detection via sherpa-onnx
  • Voice permission gates: destructive operations require spoken confirmation

Get started

User manual site (bilingual): https://qwenaudio.github.io/qwen-audio-agent/ — quick start, desktop/CLI/WebUI guides, and backend setup in one place.

Install: npm install -g qwen-audio-agent (Node.js 22+), then run qwenaudio config (DashScope API key + backend choice), then qwenaudio tui to start talking. Interfaces: macOS floating orb (custom skins since v1.7.0), TUI, and Web UI (English interface since v1.8.1).

Supported backends (ACP)

11 backends: Qwen Code (default), Claude Code, Codex CLI, OpenCode, OpenClaw, Qoder, Hermes, Kimi CLI, CodeBuddy, DeepSeek Harness, and Pi — any ACP-capable agent plugs in. See Supported Backends.

Links

Clone this wiki locally