voicy
Voicy (@voicybot): a Telegram bot that turns voice messages into text in groups and private chats
Runs with mockssource: GitHubhomepageJavaScriptMITcommit 2b8960bbaa89
JavaScript, MIT licensed. The project labels itself: bot, speech recognition, speech to text, telegram, telegram bot, transcription, voice messages and voice to text.
voicy 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.
TypeScript compiles cleanly, Express webhook server starts and enforces authentication, and 31 unit/proof tests pass against an in-memory MongoDB, covering transcription caching, job lifecycle, abuse limits, donation formatting, webhook handling, and activity stream emitters
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 90 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.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- batch test runner had 4 transient failures from MongoDB instance port contention between parallel MongoMemoryServer instances3 minutes
- Install time
- 1 minutes
- Cold machine to finish
- 4 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- yarn build-ts exited 0; 31 individual proof scripts all pass (node scripts/*-proof.js); Express server responded with expected status codes on /worker/v1/jobs/claimable (401 no auth, 400 invalid_job_id with valid auth) and POST / (400 Webhook error with bad stripe sig); in-memory MongoDB connected and served all model-dependent tests
- Model tokens used
- 130,520
- Exact commit tested
- 2b8960bbaa89
- 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.
Let me calculate elapsed time: exec /bin/sh -lc 'echo "Start time roughly 22:15 UTC, now approximately:" && date -u' in /work/repo succeeded in 0ms: Start time roughly 22:15 UTC, now approximately: Fri Nov 20 22:19:57 UTC 2026 About 5 minutes. Let me clean up and output the result: 2026-11-20T22:19:59.045605Z ERROR codex_core::tools::router: error=exec_command failed: CreateProce… That's fine, the temp files in /tmp don't matter. tokens used 130,520 That's fine, the temp files in /tmp don't matter.
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 4 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.
- 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.
Of the 5 bot projects Argusic has installed and timed, voicy was the 2nd fastest to reach a running state, and 2 of 5 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 | 2/3 | Runs with mocks | 92.00 | 0.05 | |
| Argusic Runner | 1/3 | Runs with mocks | 88.00 | 0.06 |
Topics (from GitHub)
botspeech-recognitionspeech-to-texttelegramtelegram-bottranscriptionvoice-messagesvoice-to-text
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/voicy)Questions
- Does voicy run?
- voicy 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 voicy?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 2b8960bbaa89. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test voicy?
- 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 voicy 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 voicy need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing voicy?
- 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 voicy compare with the alternatives?
- Of the 5 bot projects Argusic has installed and timed, voicy was the 2nd fastest to reach a running state, and 2 of 5 reached one at all.
- Where is the evidence for voicy?
- 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.