What problem does it solve? Producing accurate, well-timed subtitles for video or audio requires transcription, timestamp alignment, format validation, and rendering—steps that are error-prone when done manually. This Skill manages the full subtitle pipeline with local-first handling and explicit timing verification. ## Core Features & Use Cases - Transcription and Subtitle Generation: Convert speech to timestamped Traditional Chinese subtitles using local Whisper-compatible engines or supplied transcripts, with glossary support for names and technical terms. - Validation and Conversion: Generate SRT from structured cue JSON and check sequence numbers, timestamps, overlaps, and empty captions before rendering. - Styling, Translation, and Burning: Apply bilingual layouts, ASS styling, and burn subtitles into H.264/AAC MP4 or attach soft subtitle tracks. - Use Case: You have a phone-recorded tutorial video and need Traditional Chinese captions. The Skill transcribes the audio, splits captions at phrase boundaries, validates the SRT, previews the font rendering, and delivers both the editable SRT and a burned MP4. ## Quick Start Use the video-subtitle skill to transcribe my video and produce validated Traditional Chinese SRT subtitles plus a burned-in MP4 version.
