Clips AI

Clips AI is an open source Python library that automatically converts long form video into short clips. With a few lines of code a developer can segment a video into multiple clips and resize it from a 16:9 landscape aspect ratio to 9:16 vertical, ready for short video platforms. It is designed for developers building their own video repurposing workflows, and it works best with audio centric, narrative videos such as podcasts, interviews, speeches and sermons. The clipping algorithm works from the transcript: the video is first transcribed with WhisperX, an open source wrapper around Whisper that detects word level timing, and the ClipFinder class then identifies clip boundaries. The resizing algorithm reframes the video to focus on the current speaker, using Pyannote for speaker diarization, which requires a Hugging Face access token. Installation is through pip, with libmagic and ffmpeg as additional dependencies. There is no pricing page. The library itself is free and open source, and the documentation site covers a quickstart plus reference pages for clipping and resizing. Any cost comes from the compute you run it on. Note that this is a code library rather than a hosted editing app, so it suits engineers rather than creators looking for a point and click clip maker.