mimi

把电脑或麦克风声音转成实时翻译字幕。Live translated subtitles from computer or microphone audio.

Runs with mockssource: GitHubhomepageRustMITcommit 9eae2b87be80

Rust, MIT licensed. The project labels itself: android, audio capture, desktop app, linux, live captions, live translation, macos and pipewire.

mimi runs, with stand-ins for the services it depends on. An Argusic agent installed it in 36 minutes and hit 7 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

The mimi Tauri app builds, its full Rust test suite passes (421/421), the frontend builds and all TypeScript tests pass (120/120), and the release binary launches on the virtual X display, creating all three windows and registering keyboard shortcuts before staying alive until killed.

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 89.5 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
89.5 / 100
cost of the verifying run
$0.76 (measured)
recorded runs
2
last tested
stars
952
forks
61
open issues
0
watchers
2
size
177 MB
created
last push

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.

Time lost to each failure while testing mimi, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • Missing Tauri/WebKit system -dev libraries (libwebkit2gtk-4.1-dev, libgtk-3-dev, etc.)8 minutes
  • WebKit helper binaries hardcode /usr/lib/... path (not writable)5 minutes
  • Missing appindicator/dbusmenu/dbus runtime libraries for tray icon5 minutes
  • gio-2.0.pc had unsatisfed transitive pkg-config deps (zlib, mount, libselinux, freetype2, fontconfig, x11, etc.)4 minutes
  • Node.js v18 too old (requires 20+)3 minutes
  • Rust lld linker could not find extracted .so libraries3 minutes
Install time
36 minutes
Cold machine to finish
36 minutes
Errors hit and fixed
7 hit, 7 fixed with no human help
How the result was proved
cargo test: 421 passed, 0 failed; npm test: 120 passed, 0 failed; npm build: OK; release binary (8.8MB) launched on Xvfb display :99, created all three windows (overlay, tray panel, overlay control), registered both global shortcuts (session + immersive), process stayed alive through 5-second health check
Model tokens used
247,523
Exact commit tested
9eae2b87be80
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.

Frontend tests: 120 passed, 0 failed (15 test files)
Frontend lint: 0 errors
Frontend build: OK
Release binary: 8.8 MB, launches successfully
Cargo fmt: OK
App launched on virtual display :99, created all 3 windows (overlay, tray panel, overlay control), …
Here is the final report:
**ARGUSIC_RESULT:** `{"install_succeeded":true,"launch_succeeded":true,"install_minutes":36,"errors…
tokens used
247,523
Here is the final report:
**ARGUSIC_RESULT:** `{"install_succeeded":true,"launch_succeeded":true,"install_minutes":36,"errors…

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 36 minutes.
  • Recovered from all 7 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

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.

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 byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs with mocks92.000.76
Argusic Runner1/3Runs with mocks87.000.05

Topics (from GitHub)

androidaudio-capturedesktop-applinuxlive-captionslive-translationmacospipewirepulseaudioreal-time-translationrealtime-translatorspeech-recognitionspeech-to-textsubtitle-overlaysubtitlessystem-audiotauriubuntuwindows

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/mimi.svg)](https://argusic.com/subject/mimi)

Questions

Does mimi run?
mimi runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 36 minutes, hitting 7 errors on the way, and recorded the session.
How did Argusic test mimi?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 9eae2b87be80. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test mimi?
The run that produced this verdict cost $0.76: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does mimi take to install?
36 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 mimi need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing mimi?
7 things broke in the recorded run, and 7 were fixed without human help. Each one, and the time it cost, is listed on this page.
Where is the evidence for mimi?
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.

Discussion