Skip to content

Generate TikTok— and Instagram—tailored captions and hashtags for your videos using the power of some super creative robots up in the clouds ☁️ 🤖 💬 ☁️

License

Notifications You must be signed in to change notification settings

tjoab/captionaize

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Captionaize 🤖

A generative AI tool that uses Google Gemini 1.5 to parse through your videos — suggesting captions and hashtags that are tailored to your content

The tool suggest different captions/hanstags for TikTok or Instagram, since trends vary on either platform

How to Use - App

There is a nice UI that you can use to interact with the tool here

Upload your video file and away you go

How to Use - Code

Alternatively, the app can be run by cloning this repo and working with it locally

  • Clone repo

    git clone https://github.com/tjoab/captionaize.git
    cd captionaize
  • Set up your virtual enviroment using Python 3.11

    python3 -m venv venv
    source venv/bin/activate
  • Install dependencies pip3 install -r requirements.txt

    (Streamlit dependency not needed if you don't plan on running the streamlit app locally - can be removed)

  • Create a new main script file

  • Import the helper.py module to your main script

  • Add the following to your main script

    from helper import authenticateAPI, uploadVideo, modelInference, deleteVideo
    
    authenticateAPI(YOUR_GOOGLE_API_KEY)
    
    filePath = "path_to_your_video_file_in_project_dir"
    
    videoFile = uploadVideo(filePath)
    
    response = modelInference(videoFile)
    
    deleteVideo(videoFile)
  • The response variable contains the raw response from the LLM request, which can be printed directly and inspected, but it is a bit ugly. You could also import the parseResponse() function from the helper module and get a formatted tuple:

    Tuple[str, List[str], List[str]] = (Caption, List of Viral-esque Hashtags, List of Relevance-esque Hastags)

    from helper import parseResponse
    
    platform = "tiktok"
    # or
    platform = "instagram"
    
    parseResponse(response, platform)

🛠️ Built With

📄 License

This project is licensed under the MIT License - see the LICENSE.md file for details

☕ Support

If you find this project helpful, you can support me by buying a coffee:

Buy me a coffee

About

Generate TikTok— and Instagram—tailored captions and hashtags for your videos using the power of some super creative robots up in the clouds ☁️ 🤖 💬 ☁️

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages