Whisper-TikTok

From AI tools to TikTok video creation using FFMPEG, Microsoft Edge read aloud and OpenAI Whisper model

Runs with mockssource: GitHubhomepagePythonApache-2.0commit 5a0cdeef5262

Python, Apache-2.0 licensed. The project labels itself: edge tts, ffmpeg, python, text to speech, tiktok and whisper.

Whisper-TikTok runs, with stand-ins for the services it depends on. An Argusic agent installed it in 5.9 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Package installs (uv sync --frozen), CLI help works, list-voices queries real Edge TTS API returning 9 Male + 8 Female English voices, create pipeline runs end-to-end with yt-dlp YouTube download, Whisper transcription, FFmpeg video composition delivering a valid 2.3MB MP4, and pytest passes 1/1.

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

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.04 (measured)
recorded runs
1
last tested
stars
344
forks
55
open issues
1
watchers
7
size
28 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 Whisper-TikTok, 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.

  • Edge TTS streaming API returned 403 (WSS handshake rejected) from container, blocking TTS synthesis step0.7 minutes
  • yt-dlp -o '%(id)s.%(ext)s' format string unquoted in video_downloader.py; shell interpreted %(id)s as subshell syntax0.5 minutes
  • subprocess.Popen in command_executor.py passed command string without shell=True, treating entire string as executable name0.3 minutes
Install time
6 minutes
Cold machine to finish
7 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
uv run whisper_tiktok list-voices --language en-US --gender Male returned 9 real voices; uv run whisper_tiktok list-voices --language en-US --gender Female returned 8 real voices; uv run whisper_tiktok create --model tiny ran full pipeline (yt-dlp download -> TTS fallback -> Whisper tiny transcribe -> FFmpeg compose); ffmpeg -v error -i output.mp4 -f null - returned zero errors on 2.3MB output; pytest tests/ -v: 1 passed
Model tokens used
190,039
Exact commit tested
5a0cdeef5262
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.

asyncio: mode=Mode.STRICT, debug=False, asyncio_default_fixture_loop_scope=None, asyncio_default_te…
created: 128/128 workers
128 workers [1 item]
scheduling tests via LoadScheduling
tests/test_import.py::test_whisper_tiktok_import
[gw0] [100%] PASSED tests/test_import.py::test_whisper_tiktok_import
Learn more about nbmake at https://github.com/treebeardtech/nbmake
============================== 1 passed in 34.11s ==============================
The full pipeline ran end-to-end and the output video is valid. Let me record the final verified st…
tokens used
190,039
The full pipeline ran end-to-end and the output video is valid. Let me record the final verified st…

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 5.9 minutes.
  • Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed Apache-2.0, 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.

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 Runner1/3Runs with mocks92.000.04

Topics (from GitHub)

edge-ttsffmpegpythontext-to-speechtiktokwhisper

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/Whisper-TikTok.svg)](https://argusic.com/subject/whisper-tiktok)

Questions

Does Whisper-TikTok run?
Whisper-TikTok runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 6 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test Whisper-TikTok?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 5a0cdeef5262. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test Whisper-TikTok?
The run that produced this verdict cost $0.04: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does Whisper-TikTok take to install?
5.9 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 Whisper-TikTok need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing Whisper-TikTok?
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.
Where is the evidence for Whisper-TikTok?
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.

Discussion