captionaize Download - captionaize Source code download

captionaize

AI Source Code

1.0.0

Download

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)
```