video-assembly

Video assembly uses ffmpeg to combine image sequences and audio tracks into a final MP4. The Skill automates timing calculations, frame-rate matching, and h.264 encoding to synchronize multi-scene visuals with narration in a single output file.

Audio concatenation with ffmpeg joins scene-level MP3 or audio files into a single continuous track. This Skill provides Bash scripts that handle the concatenation, timing alignment, and integration with video encoding in one pipeline.

The Skill enforces STYLE_LOCK and CHARACTER_LOCK constraints across six scenes to maintain visual and tonal consistency. It maps ElevenLabs voice output to scene timing, then uses ffmpeg to synchronize each image with its corresponding narrated audio segment.

Frame timing calculation ensures even pacing by dividing audio duration by scene count and converting to frame counts at your target frame rate. This Skill automates those calculations in the Bash pipeline so each image displays for the correct duration.

Yes. The Skill handles six-scene narratives with consistent characters and styling, making it suitable for educational content, children's stories, and social-media videos where synchronized visuals and professional narration are required.

The Skill handles h.264 encoding automatically. The ffmpeg-based pipeline accepts your image and audio inputs, applies proper resolution and codec settings, and outputs a final MP4 without manual encoding steps.