earshot
Ears for coding agents: let AI hear, review and make sound. CPU-only, open source.
Runs with mockssource: GitHubPythonMITcommit 591fa3e02803
Python, MIT licensed. The project labels itself: ai agents, audio, claude code, mcp and sound design.
earshot runs, with stand-ins for the services it depends on. An Argusic agent installed it in 1 minute and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
earshot 0.4.0 installed with all dependencies. CLI responds to all commands (earshot --help, measure, sfx, kit, etc.). The procedural sound bank (252 sounds) renders deterministically. Test suite: 797 pass (fast tests), 21 skip (model-dependent/--slow). The MCP stdio server starts and registers all tools.
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 92 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page. 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.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- 12 test_interfaces.py tests failed: FakeRequests SLEEP pollution from subprocess via global time.sleep monkeypatch (8 LLM tests) + missing 'mcp' module (4 MCP tests)3 minutes
- Install time
- 1 minutes
- Cold machine to finish
- 32 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- pytest tests/ -> 797 passed, 21 skipped in 278s; earshot measure on a synthetic WAV returned peak/LUFS/envelope; bank.render('click/soft') returned deterministic 4501 samples
- Model tokens used
- 219,958
- Exact commit tested
- 591fa3e02803
- 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
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
/bin/sh -lc "cd /work/repo && echo \"ARGUSIC_RESULT: {\\\"install_succeeded\\\":true,\\\"launch_suc…
succeeded in 0ms:
The ARGUSIC_RESULT line has been printed. Here's a summary of what was done:
- **Installed**: Python 3.12.3 venv, torch 2.15.0 CPU, all deps (transformers, librosa, mcp, etc.),…
- **Fixed 12 test failures**: Two root causes — (1) the `fake` fixture patched `time.sleep` globall…
- **Verified**: 797/797 fast tests pass, CLI measures audio correctly, sound bank renders 252 proce…
tokens used
219,958
The ARGUSIC_RESULT line has been printed. Here's a summary of what was done:
- **Installed**: Python 3.12.3 venv, torch 2.15.0 CPU, all deps (transformers, librosa, mcp, etc.),…
- **Fixed 12 test failures**: Two root causes — (1) the `fake` fixture patched `time.sleep` globall…
- **Verified**: 797/797 fast tests pass, CLI measures audio correctly, sound bank renders 252 proce…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
- Installed in 1 minute, faster than the median of the 114 comparable projects Argusic has measured.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 115 ai-agents projects Argusic has installed and timed, earshot was the 18th fastest to reach a running state, and 85 of 115 reached one at all.
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 | 1/3 | Runs with mocks | 92.00 | 0.30 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/earshot)Questions
- Does earshot run?
- earshot runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test earshot?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 591fa3e02803. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test earshot?
- The run that produced this verdict cost $0.30: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does earshot take to install?
- 1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does earshot need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing earshot?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does earshot compare with the alternatives?
- Of the 115 ai-agents projects Argusic has installed and timed, earshot was the 18th fastest to reach a running state, and 85 of 115 reached one at all.
- Where is the evidence for earshot?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.