Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/gabrielelanzafamee/viral-clips-extractor
Extract the most viral clips from a random youtube video.
https://github.com/gabrielelanzafamee/viral-clips-extractor
automation chatgpt clips extractor face-detection moviepy opencv python speech-to-text text-to-text
Last synced: about 1 month ago
JSON representation
Extract the most viral clips from a random youtube video.
- Host: GitHub
- URL: https://github.com/gabrielelanzafamee/viral-clips-extractor
- Owner: gabrielelanzafamee
- Created: 2023-09-18T23:18:21.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-11-07T13:57:54.000Z (2 months ago)
- Last Synced: 2024-11-27T10:38:42.221Z (about 2 months ago)
- Topics: automation, chatgpt, clips, extractor, face-detection, moviepy, opencv, python, speech-to-text, text-to-text
- Language: Python
- Homepage:
- Size: 47.3 MB
- Stars: 29
- Watchers: 5
- Forks: 5
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- Funding: FUNDING.yml
Awesome Lists containing this project
README
# Viral Clips Extractor
This is a clips extractor tool that allows you to extract the most viral, funny, or interesting parts of a YouTube video based on the transcript, create subtitles, and crop the video around detected faces using OpenCV. It leverages the power of Whisper Timestamped for transcript extraction and ChatGPT 3.5 for content analysis.
## Overview
This tool provides a convenient way to:
1. Extract the transcript of a YouTube video using whisper_timestamped.
2. Analyze the transcript with ChatGPT 3.5 to identify the most engaging parts.
3. Cut the video at the identified times to create shorter clips.
4. Generate subtitles for the clips.
5. Automatically crop the video to focus on the detected faces using OpenCV.
## Requirements
To run the YouTube Clips Extractor, you'll need the following:
- FFMPEG
- ImageMagick
- Check the `requirements.txt` file.
## Installation
1. Clone this repository:
```shell
git clone https://github.com/xjabr/viral-clips-extractor.git
```
2. Install the required Python packages:
```shell
pip install -r requirements.txt
```
3. Sign up for ChatGPT 3.5 and obtain your API credentials.
4. Configure the API credentials for ChatGPT 3.5 by update the variable `openai.api_key` in `contents/chatgpt.py` file in the project directory.
```python
openai.api_key = ''
```
5. Export cookies from tiktok.com using "Get cookies.txt LOCALLY" and save it in the root of the project as `cookies.txt`
6. Run the application:
```shell
python clips_extractor.py --url
```
## Contributors
This project was developed by:
- Gabriele Lanzafame (@xjabr) - [GitHub Profile](https://github.com/xjabr)
If you'd like to contribute or report issues, please feel free to open an [issue](https://github.com/xjabr/viral-clips-extractor/issues) or submit a [pull request](https://github.com/xjabr/viral-clips-extractor/pulls).
## Acknowledgments
We would like to thank the following libraries and services for making this project possible:
- [moviepy](https://github.com/Zulko/moviepy) by Zulko
- [whisper-timestamped](https://github.com/linto-ai/whisper-timestamped) by linto-ai
- [ChatGPT 3.5](https://beta.openai.com/signup/) by OpenAI
- [OpenCV](https://opencv.org/) for face detection and video manipulation
Your contributions and feedback are highly appreciated!