Clips AI

What is Clips AI?

Clips AI is an open-source Python library that splits long videos into smaller clips and resizes them to different aspect ratios with just a few lines of code. It is built for narrative, audio-driven videos such as podcasts, interviews, speeches, and sermons.

The library analyzes a video’s transcript to determine the best places to cut clips. Its resizing feature then automatically reframes the video to keep the current speaker front and center.

Who created Clips AI?

Clips AI was developed by M. Bain, which focuses on an open-source Python library that automates turning long videos into shareable clips.

What is Clips AI used for?

• Automatic clipping: A clipping algorithm analyzes transcripts to identify and create clips from long videos.
• Dynamic reframing: A resizing algorithm keeps the current speaker in focus.
• Aspect ratio conversion: Changes aspect ratios, such as 16:9 to 9:16, with minimal code.
• Transcription: Uses WhisperX to transcribe videos, capturing the start and stop time of each word.
• Speaker diarization: Uses Pyannote to identify different speakers; a Hugging Face access token is required for resizing via Pyannote, with detailed instructions available on its HuggingFace page.
• Trimming: Lets you trim your original video into the clips you want.

Who is Clips AI for?

• Podcasters
• Interviewers
• Speakers
• Clergy
• Anyone creating audio-centric, narrative-based content

Getting started

To use Clips AI, first transcribe your video with WhisperX, which provides word-level start and stop times. You will also need a Hugging Face access token to resize videos using Pyannote for speaker diarization. Detailed instructions for Pyannote are available on its HuggingFace page.

Alternatives

For creating professional videos without editing skills, consider platforms like Hour One AI. For automated video generation, transcription, collaboration, optimization, and publishing, Peech AI is another option.