Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/adhikary97/Sharetape-Open-Source
Script that takes any long form video or podcast and outputs clips for social media
https://github.com/adhikary97/Sharetape-Open-Source
instagram-reels nlp podcast tiktok video-clipper video-clips youtube
Last synced: 3 months ago
JSON representation
Script that takes any long form video or podcast and outputs clips for social media
- Host: GitHub
- URL: https://github.com/adhikary97/Sharetape-Open-Source
- Owner: adhikary97
- License: mit
- Created: 2023-06-25T22:10:12.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2023-12-27T04:02:55.000Z (11 months ago)
- Last Synced: 2024-05-29T05:10:20.314Z (6 months ago)
- Topics: instagram-reels, nlp, podcast, tiktok, video-clipper, video-clips, youtube
- Language: Python
- Homepage: https://sharetape.ai/waitlist
- Size: 148 KB
- Stars: 95
- Watchers: 5
- Forks: 6
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Sharetape-Open-Source
This script uses NLP to determine the 10 best topics from a podcast or long form video. Then based on these topics it cuts 30-60 second clips for TikTok, Instagram, or YouTube Shorts. You can even crop the video to 9:16 format and add captions if needed.
## Demo
[Sharetape Open Source Demo](https://www.youtube.com/watch?v=lPDF0VG9sbk)
## Install homebrew dependencies
```
$ brew install ffmpeg
$ brew install imagemagick
```
## Install requirements
```
$ python3 -m venv venv
$ source venv/bin/activate
$ pip install -r requirements.txt
```
## Download Vosk Library
This is the language library this speech to text uses. Download this [Here](https://alphacephei.com/vosk/models/vosk-model-en-us-0.42-gigaspeech.zip)
Once downloaded unzip in your project directory.
## Execution
There are 4 flags
- `-v` or `-video` is the video path. Only `.mov` or `.mp4`
- `-c` or `-crop` crops the video to 9:16 format, default is `False`
- `-ca` or `-captions` adds captions, default is `False`
- `-cl` or `-clipLength` is length of clip, default is `30 seconds`
Clips will be output in a directory with a unique ID i.e. `c088af43-362b-4837-bf29-d9122008f457/clips`
Example:
```
$ python main.py -v 1086final.mov -c True -ca True -cl 60
```