mangox-ai/ai-video-downloader — explained in plain English
Analysis updated 2026-05-18
Download a video from YouTube, TikTok, or another platform with one command.
Generate a Vietnamese dubbed version of a foreign language video automatically.
Bulk download videos from a Douyin user profile using a headless browser.
| mangox-ai/ai-video-downloader | 0311119/free_registertool | 18597990650-lab/multi-agent-game | |
|---|---|---|---|
| Stars | 24 | 24 | 24 |
| Language | Python | Python | Python |
| Setup difficulty | moderate | hard | moderate |
| Complexity | 2/5 | 4/5 | 3/5 |
| Audience | general | developer | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires ffmpeg and yt-dlp on the system plus a text to speech API key from Vbee, ElevenLabs, or OpenAI.
This project is a set of Claude Code skills for downloading videos from the internet and generating Vietnamese-language voice-overs from them. The README is written entirely in Vietnamese. The tools are designed to let someone watch foreign-language video content offline with automatic Vietnamese dubbing, without needing to understand the original language. There are three slash commands. The first, /video-download, takes a URL and downloads the video using yt-dlp, a widely-used command-line downloader that supports YouTube, TikTok, Instagram, Facebook, Bilibili, Douyin, Twitter/X, Vimeo, and many other platforms. The second, /voice-over, takes the folder where a video was saved and runs a pipeline: it transcribes the audio using Whisper (an audio-to-text tool), translates the transcript into Vietnamese, generates a Vietnamese audio track using a text-to-speech service, and combines the new audio with the original video file to produce a finished output file. The system reads API keys from a configuration file to determine which text-to-speech provider to use, with options including Vbee, ElevenLabs, and OpenAI. The third command, /douyin-crawler, handles bulk downloading from Douyin user profiles or feed pages using a headless browser. After processing, each video ends up in a folder containing the original video, metadata, a Whisper transcript, a Vietnamese translation, a Vietnamese subtitle file, the generated audio, and the final dubbed video. Installation requires ffmpeg and yt-dlp on the system, plus a Python environment with the project's dependencies and Playwright for the Douyin crawler. The project is released under the MIT license, and the author notes that it is intended only for personal use and that users are responsible for complying with the terms of service of each platform.
Claude Code skills that download videos from social platforms and generate Vietnamese dubbed versions using speech transcription and text to speech.
Mainly Python. The stack also includes Python, yt-dlp, Whisper.
Use freely for any purpose, including commercial use, as long as you keep the copyright notice.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly general.
This repo across BitVibe Labs
Verify against the repo before relying on details.