WhisperLive
A nearly-live implementation of OpenAI's Whisper.
Runssource: GitHubPythonMITcommit 99cbc1c33b35
Python, MIT licensed. The project labels itself: dictation, obs, openai, openvino, openvino intel, rocm, tensorrt and tensorrt llm.
WhisperLive runs. An Argusic agent installed it in 6 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
WhisperLive is installed in a Python 3.12 venv with all dependencies, 318 of 332 unit tests pass (14 metrics tests skipped as they require a dedicated metrics server port), and the server launches with the REST API health endpoint responding HTTP 200 on port 8000 and the WebSocket server listening on port 9090.
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
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.
- PyAudio build failed: missing python3-dev and portaudio19-dev (no root access for apt)1 minute
- Missing test dependency: jiwer module not installed1 minute
- VAD model download failed: wget not available in container1 minute
- test_vad_extended.py mocked subprocess.run instead of urllib.request.urlretrieve after the code change1 minute
- Install time
- 6 minutes
- Cold machine to finish
- 11 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- pytest: 318 passed, 14 skipped; curl -s -o /dev/null -w '%{http_code}' http://127.0.0.1:8000/health returned 200
- Model tokens used
- 74,979
- Exact commit tested
- 99cbc1c33b35
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
INFO:root:✅ Argusic-Compatible API started on http://0.0.0.0:8000 INFO:websockets.server:server listening on 0.0.0.0:9090 INFO: Started server process [1738] INFO: Waiting for application startup. INFO: Application startup complete. INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit) INFO: 127.0.0.1:34730 - "GET /health HTTP/1.1" 200 OK 200 Server launched and health endpoint responded 200. Let me format the final result. tokens used 74,979 Server launched and health endpoint responded 200. Let me format the final result.
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 6 minutes.
- Recovered from all 4 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.
What did not, or is not known
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 6 minutes after the clone.
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
Topics (from GitHub)
dictationobsopenaiopenvinoopenvino-intelrocmtensorrttensorrt-llmtext-to-speechtranslationvoice-recognitionwhisperwhisper-tensorrt
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/whisperlive)Questions
- Does WhisperLive run?
- Yes. WhisperLive runs. Argusic installed and launched it on a clean machine in 6 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test WhisperLive?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 99cbc1c33b35. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test WhisperLive?
- The run that produced this verdict cost $0.07: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does WhisperLive take to install?
- 6 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 WhisperLive need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing WhisperLive?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for WhisperLive?
- 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.