Skip to content

๐Ÿš€๐ŸŽฌ ShortGPT - Experimental AI framework for youtube shorts / tiktok channel automation

License

Notifications You must be signed in to change notification settings

juanfariasdev/ShortGPT

ย 
ย 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 

Repository files navigation

๐Ÿš€๐ŸŽฌ ShortGPT

AI video automation framework

ShortGPT-logo
โšก Automating video and short content creation with AI โšก

Follow the installation steps below for running the web app locally (running the google Colab is highly recommanded). Please read "installation-notes.md" for more details.

๐ŸŽฅ Showcase (Full video on YouTube)

quickshowcase.mp4

๐ŸŽฅ Voice Dubbing

ShortGPT.video.to.video.dubbing.and.voice.translation.mp4

๐ŸŒŸ Show Your Support

We hope you find ShortGPT helpful! If you do, let us know by giving us a star โญ on the repo. It's easy, just click on the 'Star' button at the top right of the page. Your support means a lot to us and keeps us motivated to improve and expand ShortGPT. Thank you and happy content creating! ๐ŸŽ‰

GitHub star chart

๐Ÿ› ๏ธ How it works

alt text

๐Ÿ“ Introduction to ShortGPT

ShortGPT is a powerful framework for automating content creation. It simplifies video creation, footage sourcing, voiceover synthesis, and editing tasks. Of the most popular use-cases of ShortGPT is youtube automation and Tiktok creativity program automation.

  • ๐ŸŽž๏ธ Automated editing framework: Streamlines the video creation process with an LLM oriented video editing language.

  • ๐Ÿ“ƒ Scripts and Prompts: Provides ready-to-use scripts and prompts for various LLM automated editing processes.

  • ๐Ÿ—ฃ๏ธ Voiceover / Content Creation: Supports multiple languages including English ๐Ÿ‡บ๐Ÿ‡ธ, Spanish ๐Ÿ‡ช๐Ÿ‡ธ, Arabic ๐Ÿ‡ฆ๐Ÿ‡ช, French ๐Ÿ‡ซ๐Ÿ‡ท, Polish ๐Ÿ‡ต๐Ÿ‡ฑ, German ๐Ÿ‡ฉ๐Ÿ‡ช, Italian ๐Ÿ‡ฎ๐Ÿ‡น, Portuguese ๐Ÿ‡ต๐Ÿ‡น, Russian ๐Ÿ‡ท๐Ÿ‡บ, Mandarin Chinese ๐Ÿ‡จ๐Ÿ‡ณ, Japanese ๐Ÿ‡ฏ๐Ÿ‡ต, Hindi ๐Ÿ‡ฎ๐Ÿ‡ณ,Korean ๐Ÿ‡ฐ๐Ÿ‡ท, and way over 30 more languages (with EdgeTTS)

  • ๐Ÿ”— Caption Generation: Automates the generation of video captions.

  • ๐ŸŒ๐ŸŽฅ Asset Sourcing: Sources images and video footage from the internet, connecting with the web and Pexels API as necessary.

  • ๐Ÿง  Memory and persistency: Ensures long-term persistency of automated editing variables with TinyDB.

If you prefer not to install the prerequisites on your local system, you can use the Google Colab notebook. This option is free and requires no installation setup.

  1. Click on the link to the Google Colab notebook: https://colab.research.google.com/drive/1_2UKdpF6lqxCqWaAcZb3rwMVQqtbisdE?usp=sharing

  2. Once you're in the notebook, simply run the cells in order from top to bottom. You can do this by clicking on each cell and pressing the 'Play' button, or by using the keyboard . Enjoy using ShortGPT!

Instructions for running shortGPT locally

This guide provides step-by-step instructions for installing shortGPT and its dependencies. To run ShortGPT locally, you need Docker.

Installation Steps

To run ShortGPT, you need to have docker. Follow the instructions "installation-notes.md" for more details.

  1. For running the Dockerfile, do this:
docker build -t short_gpt_docker:latest .
docker run -p 31415:31415 --env-file .env short_gpt_docker:latest

Running runShortGPT.py Web Interface

  1. After running the script, a Gradio interface should open at your local host on port 31415 (http://localhost:31415)

Framework overview

  • ๐ŸŽฌ The ContentShortEngine is designed for creating shorts, handling tasks from script generation to final rendering, including adding YouTube metadata.

  • ๐ŸŽฅ The ContentVideoEngine is ideal for longer videos, taking care of tasks like generating audio, automatically sourcing background video footage, timing captions, and preparing background assets.

  • ๐Ÿ—ฃ๏ธ The ContentTranslationEngine is designed to dub and translate entire videos, from mainstream languages to more specific target languages. It takes a video file, or youtube link, transcribe it's audio, translates the content, voices it in a target language, adds captions , and gives back a new video, in a totally different language.

  • ๐ŸŽž๏ธ The automated EditingEngine, using Editing Markup Language and JSON, breaks down the editing process into manageable and customizable blocks, comprehensible to Large Language Models.

๐Ÿ’ก ShortGPT offers customization options to suit your needs, from language selection to watermark addition.

๐Ÿ”ง As a framework, ShortGPT is adaptable and flexible, offering the potential for efficient, creative content creation.

More documentation incomming, please be patient.

Technologies Used

ShortGPT utilizes the following technologies to power its functionality:

  • Moviepy: Moviepy is used for video editing, allowing ShortGPT to make video editing and rendering

  • Openai: Openai is used for automating the entire process, including generating scripts and prompts for LLM automated editing processes.

  • ElevenLabs: ElevenLabs is used for voice synthesis, supporting multiple languages for voiceover creation.

  • EdgeTTS: Microsoft's FREE EdgeTTS is used for voice synthesis, supporting way many more language than ElevenLabs currently.

  • Pexels: Pexels is used for sourcing background footage, allowing ShortGPT to connect with the web and access a wide range of images and videos.

  • Bing Image: Bing Image is used for sourcing images, providing a comprehensive database for ShortGPT to retrieve relevant visuals.

These technologies work together to provide a seamless and efficient experience in automating video and short content creation with AI.

๐Ÿ’ Contributing

As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it would be in the form of a new feature, improved infrastructure, or better documentation.

Star History Chart

About

๐Ÿš€๐ŸŽฌ ShortGPT - Experimental AI framework for youtube shorts / tiktok channel automation

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 99.5%
  • Dockerfile 0.5%