What problem does it solve? Translating a video into another language normally requires a manual chain of transcription, translation, voice cloning, TTS, audio replacement, and subtitle work. This Skill collapses that into a single orchestrated pipeline that dubs a video while preserving each speaker's original voice and returns an A/V-synced result. ## Core Features & Use Cases - One-call dubbing with voice preservation: The dub worker transcribes, translates, and re-voices the speech in the original speaker's voice, keeping the background music bed by default. - Lipsync and captions: Lipsync is ON by default for videos up to 5 minutes, and target-language or bilingual (original + translated) captions are burned onto the final video. - Segmented multi-language dubbing: Different time ranges of one video can be dubbed into different languages using a timestamped transcript plan, with uncovered ranges keeping the original audio. - Use Case: A creator asks to "make this product demo Spanish with bilingual subtitles" — the Skill dubs the video to Spanish, re-matches the speaker's mouth movements, and burns Spanish captions on top with the English original below. ## Quick Start Translate this video into Japanese with lipsync and bilingual subtitles: <video-url> --to ja --bilingual-subtitles.
