I need a small desktop application for Windows that can do two things in one flow: strip vocals from a song and then generate a time-aligned lyric file that syncs automatically with the remaining instrumental. My ideal workflow is simple—users drop an audio track onto the window, the app processes it, and out comes: • a vocal-free version of the song • a perfectly timed .lrc (or similar) file ready for karaoke or video captioning The interface should be no more than a single drag-and-drop zone plus a progress bar; everything else can live in a settings panel or run with smart defaults. If supporting additional upload methods makes sense later, keep the architecture flexible, but drag-and-drop is the must-have for the first release. On the audio side, I expect the usual formats—think MP3, WAV, FLAC—to work out of the box or via an easily extendable codec layer. For vocal removal, feel free to leverage proven libraries (e.g., Spleeter, Demucs) so development time stays focused on a clean GUI and reliable sync algorithm. The lyric syncing can be machine-learning based or onset-detection based; accuracy matters more than the underlying method, so explain your approach in your bid. Acceptance criteria • Stand-alone Windows installer and portable .exe • Drag-and-drop initiates full process without additional clicks • Output instrumental and synced lyric file in the same folder as the source track • Average processing time under two minutes for a 4-minute MP3 on a mid-range PC • Clearly commented source code and brief README covering build steps Let me know which libraries or models you intend to use, any licensing considerations, and an estimated timeline for a workable first build.