AI2026
Mubah
Turn any video into a permissible copy, on your own Mac.
A local-only Mac tool that removes music and blurs women full-body in a video, from a file or a URL. Nothing leaves the machine and working files are purged when the job finishes. Ships with an honest account of what it cannot do.
- Production
- Mubah
- Role
- Solo
- Year
- 2026
- Status
- Live
- Format
- AI
- Built with
- Pythonuvffmpegyt-dlpApple Silicon / MPSStem separationPose & person detection
- Where to find it
- Source
Treatment
Mubah is the desktop counterpart to Naqi: same intent, different constraints. A Mac has more memory and a real GPU, so it can run heavier models and take a whole file rather than working around a phone's limits.
«مباح» نظير «نقيّ» على سطح المكتب: النية ذاتها والقيود مختلفة. فجهاز Mac يملك ذاكرة أكبر ومعالجًا رسوميًا حقيقيًا، فيستطيع تشغيل نماذج أثقل ومعالجة ملف كامل بدل الالتفاف حول حدود الهاتف.
It runs from a CLI with fast, balanced and thorough presets, accepts local files or anything yt-dlp can fetch, and can output audio only. Peak measured memory use is around 2.1 GB, so 8 GB of RAM is enough.
يعمل من سطر الأوامر بإعدادات سريع ومتوازن ودقيق، ويقبل ملفات محلية أو أي شيء يستطيع yt-dlp جلبه، ويمكنه إخراج الصوت وحده. وذروة الذاكرة المقاسة نحو 2.1 غيغابايت، فثمانية غيغابايت تكفي.
The README states the limitations before the features: music removal keeps all vocals, so songs come out a-cappella; the detectors are unreliable on animation; and the filtering is automated with a fail-safe bias, so output should be verified before it is relied on.
يذكر الـ README القيود قبل الميزات: إزالة الموسيقى تُبقي كل الأصوات البشرية، فتخرج الأغاني بلا موسيقى؛ والكواشف غير موثوقة على الرسوم المتحركة؛ والترشيح آلي بتحيّز احترازي، فينبغي التحقق من المخرج قبل الاعتماد عليه.
Challenges
Removing music without removing singing
The problem
Stem separation splits audio into vocals, drums, bass and other. Dropping everything but vocals removes the instruments, but a sung vocal is still a vocal, so songs survive as a-cappella rather than disappearing.
What I did
Rather than pretend otherwise, this is documented as a known limitation at the top of the README with muting sung vocals on the roadmap. Overstating what a stem separator can do would have been the easier and worse option.
An uncertain detection has to fail one way
The problem
Detectors return confidence, not truth. Treating anything below the threshold as clear lets things through; treating everything above it as a person blurs men who are not the target.
What I did
The bias is set explicitly toward censoring: uncertain people get blurred, and an occasionally blurred man is the accepted cost. Choosing the failure direction on purpose is the whole design decision.
Results
- Fully local processing on Apple Silicon; working files purged after each job.معالجة محلية بالكامل على معالجات Apple Silicon، مع محو الملفات المؤقتة بعد كل مهمة.
- CLI with fast / balanced / thorough presets, file or URL input.سطر أوامر بإعدادات سريع/متوازن/دقيق، ومدخلات ملف أو رابط.
- Limitations documented up front rather than discovered by users.قيود موثّقة مسبقًا بدل أن يكتشفها المستخدمون.