clipify

You can convert long videos into vertical clips with captions by automating segment detection, trimming, and 9:16 reformatting while burning word-by-word subtitles using Whisper transcription and ffmpeg processing.

Automated video clipping identifies engaging segments by analyzing the video content to find notable moments like funny parts, then automatically trimming those sections to produce standalone social media clips.

You can reformat 16:9 videos to 9:16 without losing the speaker's face by applying face-following pan or split-screen reformatting techniques handled automatically through ffmpeg processing.

You need to have openai-whisper, ffmpeg, and numpy installed before processing video clips, as these dependencies handle audio transcription, video processing, and the underlying computational operations.

The best way to add word-by-word captions to a video is using Whisper for accurate transcription and ffmpeg for processing, which burns style-customizable subtitles directly into the social media clip for better engagement.

Limitations of face-following pan for social media reformatting include potential tracking issues if the video lacks clear facial features, as the ffmpeg processing relies on consistent face detection to maintain proper vertical framing.