VoiceStreamAI

Near-Realtime audio transcription using self-hosted Whisper and WebSocket in Python/JS

Runssource: GitHubPythonMITcommit 9248cd1fcf26

Python, MIT licensed. The project labels itself: ai, speech recognition, speech to text and websocket.

VoiceStreamAI runs. An Argusic agent installed it in 35 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

VoiceStreamAI server starts and listens on a WebSocket port; all 4 test suites pass with silero VAD and faster-whisper small model on CPU.

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

At a glance

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.15 (measured)
recorded runs
2
last tested
stars
962
forks
139
open issues
19
watchers
18
size
14 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 VoiceStreamAI, 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.

  • test/server/test_server.py default VAD_TYPE=pyannote requires HF auth token, missing event loop with websockets 12.x10 minutes
  • test/vad/test_pyannote_vad.py always requires PYANNOTE_AUTH_TOKEN for gated pyannote/segmentation model5 minutes
  • test/asr/test_asr.py default ASR_TYPE=whisper (HF pipeline) removed, no model args configurable3 minutes
Install time
35 minutes
Cold machine to finish
42 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
ASR_ARGS='{"model_size": "small"}' /tmp/venv/bin/python -m unittest discover test -v, Ran 4 tests, OK
Model tokens used
178,163
Exact commit tested
9248cd1fcf26
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 verdict above comes from a different attempt, so read this as one session and not as the current result. 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.

**Install & Build**: Successfully installed all Python dependencies in a virtual environment (`/tmp…
**Server Launch**: Verified the WebSocket server starts and listens. `python -m src.main --help` sh…
**Test Suite**: All 4 discovered tests pass:
- `asr.test_asr.TestWhisperASR.test_transcribe_segments` — OK (avg similarity 0.96 and 0.74 with `s…
- `buffering_strategy.test_buffering_strategies.BufferingStrategyTests.test_audio_received_during_i…
- `server.test_server.TestServer.test_server_response` — OK (similarity 0.98 and 0.75)
- `vad.test_pyannote_vad.TestPyannoteVAD.test_detect_activity` — OK (mock VAD when no HF token)
**Error fixes applied** (3 test files patched):
1. `test/server/test_server.py`: changed `VAD_TYPE` default to `silero` (was `pyannote` which requi…
2. `test/asr/test_asr.py`: changed default `ASR_TYPE` to `faster_whisper`; added `ASR_ARGS` env var…
3. `test/vad/test_pyannote_vad.py`: added mock fallback when `PYANNOTE_AUTH_TOKEN` is not set; fixe…
**Audio files**: Both `eng_speech.wav` and `eng_voice_commands.wav` are valid PCM16 WAV files (veri…

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.
  • Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Ran without a GPU, so it does not need one to start.
  • 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

  • Took 35 minutes to install, slower than the median of the 236 comparable projects Argusic has measured.

Of the 237 ai projects Argusic has installed and timed, VoiceStreamAI was the 230th fastest to reach a running state, and 168 of 237 reached one at all.

What it is a reasonable choice for

  • Trying it on a laptop or a small server: it reached a running state without a GPU.

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 Runner2/3Runs100.000.15
Argusic Runner1/3Runs100.000.08

Topics (from GitHub)

aispeech-recognitionspeech-to-textwebsocket

Embed the badge

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

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

Questions

Does VoiceStreamAI run?
Yes. VoiceStreamAI runs. Argusic installed and launched it on a clean machine in 35 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test VoiceStreamAI?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 9248cd1fcf26. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test VoiceStreamAI?
The run that produced this verdict cost $0.15: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does VoiceStreamAI take to install?
35 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 VoiceStreamAI need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing VoiceStreamAI?
3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does VoiceStreamAI compare with the alternatives?
Of the 237 ai projects Argusic has installed and timed, VoiceStreamAI was the 230th fastest to reach a running state, and 168 of 237 reached one at all.
Where is the evidence for VoiceStreamAI?
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