codertapsu/multilingual-dubbed-video — reverse-engineered prompt
Reverse engineered prompt
Build me a simple desktop app called VideoDubber that lets me take any video on my computer and dub it into another language without needing a cloud account or paid API keys. I want it to work mostly offline on my machine, with a first run setup that downloads the language models I pick and then just works locally after that.
The flow should feel easy. Import a video, detect or choose the source language, pick the target language and voice, transcribe the speech, translate it, generate the new voice, line it up to the original timing, mix it back into the video, and export a finished file. Let me keep some original background audio, control ducking and voice volume, and choose subtitles as none, sidecar, soft, or burned in.
Please include progress updates, editable transcript segments, and the ability to redo just one segment or step instead of starting over. Self contained installers for the main desktop platforms would be great. Look up current docs online if you need to.
Want more depth? Deep Reverse