qwen-audio-agent
A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents
Runssource: GitHubhomepageJavaScriptApache-2.0commit 439e81b8c3d0
JavaScript, Apache-2.0 licensed. The project labels itself: acp, agent, agentic ai, ai coding, claude code, codex, developer tools and opencode.
qwen-audio-agent runs. An Argusic agent installed it in 22 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
The qwen-audio-agent v1.11.0 project installs, builds, launches a Gateway serving HTTP 200 on port 3101, and passes all 1789 automated tests with zero failures.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 96 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
- Install time
- 22 minutes
- Cold machine to finish
- 9 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- npm test exited 0: root 129/130 pass (1 skip), server 1078/1078 pass, web 110/110, tui 56/56, cli 148/148, desktop 218/218, mobile 2/2, smart-cockpit 48/48 = 1789 total pass, 0 fail. curl http://127.0.0.1:3101 returned HTTP 200.
- Model tokens used
- 72,628
- Exact commit tested
- 439e81b8c3d0
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Watch the session
The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.
A recording of attempt 1, run , the attempt that decided the verdict above. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
# duration_ms 1935.895234 EXIT_CODE=0 All 1789 tests pass across all workspaces. Here is the final summary: - **Install**: Node.js 18.19.1 was bundled but the project requires ^22.22.2. Installed nvm, then u… - **Launch**: Gateway started, served HTTP 200 on `http://127.0.0.1:3101/` and WebUI HTML. Health e… - **Tests**: Full `npm test` suite passed with 0 failures. tokens used 72,628 All 1789 tests pass across all workspaces. Here is the final summary: - **Install**: Node.js 18.19.1 was bundled but the project requires ^22.22.2. Installed nvm, then u… - **Launch**: Gateway started, served HTTP 200 on `http://127.0.0.1:3101/` and WebUI HTML. Health e… - **Tests**: Full `npm test` suite passed with 0 failures.
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 22 minutes.
- Nothing broke on the way: zero errors between clone and running.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- Following its own README: the documented path worked with nothing to fix.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.02 | |
| Argusic Runner | 1/3 | Runs | 100.00 | 0.05 |
Topics (from GitHub)
acpagentagentic-aiai-codingclaude-codecodexdeveloper-toolsopencodespeech-recognitiontext-to-speechvoice-agentvoice-aivoice-chat
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/qwen-audio-agent)Questions
- Does qwen-audio-agent run?
- Yes. qwen-audio-agent runs. Argusic installed and launched it on a clean machine in 22 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test qwen-audio-agent?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 439e81b8c3d0. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test qwen-audio-agent?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does qwen-audio-agent take to install?
- 22 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does qwen-audio-agent need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing qwen-audio-agent?
- Nothing did, in the recorded run: zero errors between clone and running.
- Where is the evidence for qwen-audio-agent?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.