YouDub-webui
Open-source AI video localization and dubbing for YouTube/Bilibili: speech recognition, subtitle translation, voice cloning, audio mixing and rendering. 开源 AI 视频翻译配音工具。
Runssource: GitHubhomepageTypeScriptApache-2.0commit 0f6c75935e7a
TypeScript, Apache-2.0 licensed. The project labels itself: ai dubbing, ai video translation, bilibili, demucs, fastapi, ffmpeg, multilingual video and nextjs.
YouDub-webui runs. An Argusic agent installed it in 45 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The app is installed and running: backend answered 200 on /api/health, frontend answered 200 on :3000, all 421 backend and 14 frontend tests pass, and a local-video task ran end to end producing a final mp4 that ffprobe showed as h264+aac and ffmpeg fully decoded.
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.
- pip install -r requirements.txt failed: diffq sdist build needs Python.h (python3-dev) and we have no root8 minutes
- torchaudio resolved to CUDA build from PyPI which fails to load (libcudart.so.13 missing) against CPU torch6 minutes
- System node v18 too old for Next.js 16 (requires Node 20+)5 minutes
- End-to-end task failed at translate stage because my initial mock returned a plain string instead of the required JSON object3 minutes
- uvicorn missing from backend/requirements-test.txt so backend launch failed (No such file or directory)2 minutes
- Install time
- 45 minutes
- Cold machine to finish
- 19 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- curl -s http://127.0.0.1:8000/api/health returned 200 {"status":"ok"}; curl http://127.0.0.1:3000/ returned 200; .venv/bin/python -m pytest backend/tests exited 0 with 421 passed; npx vitest run exited 0 with 14 passed; npm run build and npm run lint exited 0; ffprobe on downloaded final-video showed h264+aac 5.0s and ffmpeg -v error -i out.mp4 -f null - exited 0
- Model tokens used
- 503,697
- Exact commit tested
- 0f6c75935e7a
- 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.
LINT_EXIT=0 > [email protected] lint > eslint I have everything I need. Let me compose the final report. **Summary of the run (what I observed):** - Installed demo-independent Python requirements: `backend/requirements-test.txt` clean; full `requ… - `421` backend and `14` frontend tests passed; frontend `build` and `lint` passed; Node 22 (needed… - App launched: backend `uvicorn` up (`/api/health` 200), frontend Next.js dev `:3000` 200. - Schema-correct mock Argusic server stood up, then a **real end-to-end local-video pipeline ran**:… 2026-11-07T06:05:42.455373Z ERROR codex_core::tools::router: error=cannot update goal because this … tokens used 503,697
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 45 minutes.
- Recovered from all 5 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 Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
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)
ai-dubbingai-video-translationbilibilidemucsfastapiffmpegmultilingual-videonextjsopen-sourcepythonspeech-to-textsubtitle-translationtext-to-speechvideo-localizationvideo-translationvoice-cloningvoxcpmwhisperyoutubeyoutube-translator
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/youdub-webui)Questions
- Does YouDub-webui run?
- Yes. YouDub-webui runs. Argusic installed and launched it on a clean machine in 45 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test YouDub-webui?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 0f6c75935e7a. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test YouDub-webui?
- The run that produced this verdict cost $0.14: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does YouDub-webui take to install?
- 45 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 YouDub-webui need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing YouDub-webui?
- 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for YouDub-webui?
- 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.