abogen
Generate audiobooks from EPUBs, PDFs and text with synchronized captions.
Runssource: GitHubhomepagePythonMITcommit 08e2ee8b85bb
Python, MIT licensed. The project labels itself: audiobook, audiobooks, content creation, content creator, ebook, epub, epub converter and kokoro.
abogen runs. An Argusic agent installed it in 11.2 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
All 1592 tests pass, Flask web UI serves HTTP 200 on GET /, and the real Kokoro-82M TTS engine with af_heart voice generates non-silent, ffmpeg-decodable WAV audio from text input.
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.
- PyQt test crashed with Aborted (no display)1.5 minutes
- Debian's externally-managed Python blocked direct pip install1 minute
- sh shell lacks source; . venv/bin/activate used instead0.5 minutes
- Install time
- 11 minutes
- Cold machine to finish
- 22 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- python -m pytest tests/ -q --tb=short returned '1592 passed, 41 warnings' in 103s; curl -s -o /dev/null -w '%{http_code}' http://localhost:8812/ returned 200; python real kokoro pipeline produced 63000 samples (2.62s) of non-silent audio (mean_abs=0.0243) validated by ffmpeg -v error -i wav -f null - exit 0
- Model tokens used
- 147,673
- Exact commit tested
- 08e2ee8b85bb
- 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 Shutdown: _stop_conversion_service done in 0.00s INFO Shutdown: _app_cleanup done in 0.03s INFO Shutdown: _restore_sleep done in 0.00s INFO Shutdown: _terminate_subprocesses done in 0.01s INFO Shutdown: all cleanups finished Server-launch verification done All systems verified. Here's the final report: 2026-09-29T04:38:56.184034Z ERROR codex_core::session: failed to record rollout items: thread 01a0e… 2026-09-29T04:38:56.184096Z ERROR codex_core::session: failed to record rollout items: thread 01a0e… tokens used 147,673 All systems verified. Here's the final report:
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 11.2 minutes.
- 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.
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.
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)
audiobookaudiobookscontent-creationcontent-creatorebookepubepub-converterkokorokokoro-82mkokoro-ttsllmmedia-generationnarratorspeech-synthesissubtitlestext-to-audiotext-to-speechttsvoice-conversionvoice-synthesis
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/abogen)Questions
- Does abogen run?
- Yes. abogen runs. Argusic installed and launched it on a clean machine in 11 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test abogen?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 08e2ee8b85bb. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test abogen?
- The run that produced this verdict cost $0.13: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does abogen take to install?
- 11.2 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 abogen need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing abogen?
- 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 abogen?
- 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.