Alos21750/UAV-Downloader

UAV Downloader for JableTV, MissAV, SupJav & Hanime1 — UAV Browser, unattended UAV Watcher, Docker/CLI, and local-first AI subtitles.

What it solves

UAV Downloader is a desktop tool designed to automate the discovery and downloading of videos from specific adult content platforms (JableTV, MissAV, SupJav, and Hanime1). It eliminates the need for manual searching and downloading by providing automated monitoring and an integrated AI-powered subtitling system that generates captions for Japanese audio without requiring external API keys.

How it works

The project operates through three primary modes:

  • UAV Browser: A GUI for manual browsing, searching, and queueing videos for download.
  • UAV Watcher: An unattended monitoring tool that scans selected categories and schedules downloads based on user preferences, automatically removing duplicates across sites.
  • Docker/CLI: A headless version for server or NAS deployments that downloads videos via URLs or a text file.

For subtitling, it uses a local pipeline: ReazonSpeech K2 v2 or whisper.cpp for Japanese speech-to-text, and FuguMT or OPUS-MT for local translation into English and Traditional Chinese. It also supports optional integration with LLM APIs (OpenAI, Anthropic, Gemini, etc.) for higher-quality translations, while keeping the audio/video files strictly on the local machine.

Who it’s for

Users who want to automate the collection of content from these specific platforms and those who require AI-generated subtitles in multiple languages without relying on cloud-based transcription services.

Highlights

  • Unattended Automation: Automatically monitors categories and schedules downloads with cross-site deduplication.
  • Local AI Subtitles: Generates .srt files for Japanese, English, and Traditional Chinese using local models (CPU-optimized) to ensure privacy.
  • Flexible Deployment: Available as standalone Windows executables, a Python package, or a Docker image.
  • Customizable Downloads: Supports various quality settings, multi-threaded downloading (up to 32 concurrent videos), and proxy configuration.

Related

  • Project
    jianchang512/pyvideotrans

    pyVideoTrans is an open‑source Python tool that automatically translates videos by chaining speech‑to‑text, AI translation, and text‑to‑speech (with optional voice cloning). It offers a GUI, WebUI, CLI, and Docker deployment, works with local models (e.g., Faster‑Whisper, F5‑TTS) or cloud APIs, and includes utilities for subtitle editing, speaker diarisation, and GPU acceleration.

  • Project
    rockbenben/subtitle-translator

    Subtitle Translator is a free, browser‑based (and CLI) tool that batch‑translates subtitle files (.srt, .ass, .vtt, .lrc) into 120+ languages. It strips timecodes locally, sends only dialogue to chosen translation APIs (traditional MT or LLM providers), then re‑inserts the original timing. Features include ~1 s per episode processing, multi‑file upload, bilingual output, context‑aware LLM translation, unlimited local caching, and full client‑side privacy.

  • Project
    tegnike/aituber-kit

    AITuberKit is an open‑source toolkit for building AI‑driven virtual characters (VTubers) that can chat, speak, and stream live. It integrates many LLMs, TTS engines, and avatar formats, and offers modes for YouTube chat, kiosk demos, and game commentary. Run locally, via Docker, or deploy to Vercel/Cloudflare. Commercial use needs a separate license.

  • Project
    jipraks/yt-short-clipper

    YT Short Clipper v2 is a Windows‑only desktop app that automatically turns a long YouTube video into vertical (9:16) short clips. It downloads the video and its original subtitles, feeds the transcript to an LLM to pick highlight segments, cuts and re‑frames each segment, burns word‑by‑word captions, and can upload the results to Repliz. Built with React + TypeScript, Tauri (Rust), and a Python side‑car using yt‑dlp, FFmpeg, and MediaPipe, it supports any OpenAI‑compatible model or an in‑app wallet‑based AI service. The project is MIT‑licensed, beta‑stage, and Windows‑only.

  • Project
    baxtree/subaligner

    Subaligner is an open‑source Python/CLI tool that synchronises subtitles with video/audio, can transcribe speech via Whisper, translate subtitles with HuggingFace models, and even train custom alignment models. It supports many subtitle and media formats, offers fast global‑shift (`single`) and high‑accuracy two‑stage (`dual`) alignment, and provides Docker, pip, and optional extras for LLM‑based features.