What it does
Upload your images day by day to our application, and instrumental music pieces will be made for each picture. These are saved together so you can look back on your days and have a more complete sensory experience with visuals and corresponding sound. Get a colourful mood dinosaur per day and grow your collection.
How we built it
We put the user input (image and short description) through Google Gemini's API, which develops the photo into a musical prompt for ElevenLabs. ElevenLabs generates a short piece of instrumental music for each picture. The image and music are stored together using Cloudinary (links to images and MP3 files) and MongoDB (collated information per entry and links to Cloudinary data) and a coloured mood dinosaur is made for the day using the mood gathered from the image and its prominent colours. A general day audio is created by blending the others and displayed.
Challenges we ran into
Our main project files in retrospect should have been smaller and had less of a scope so that it would be easy to work in parallel when doing different tasks. As it happened, sometimes we had to git revert because of merge conflicts, but it didn't cause too much of a setback.
Accomplishments that we're proud of
We're proud of our merging of colours, music, images, and writing prompts to make a diary that a person would find genuinely useful.
What we learned
We learned how to connect APIs our coding environment and use generative AI within our codespace. It was a great chance to use software from ElevenLabs and MongoDB etc, and working with multimedia was very fun.
Built With
- gemini-api
- javascript
- python
