HackStack

Project Info

Memody

Devpost

Inspiration

The inspiration for Memody came from understanding how the human brain processes information through multiple sensory channels. Research shows that multi-modal learning - combining visual and auditory inputs - can significantly enhance memory retention and comprehension. This will be extraordinarily helpful for learners with dyslexia and ADHD. We were also inspired by how music has been used throughout history as a memorization tool, from ancient oral traditions to modern educational songs. By transforming text into music, we're creating a new way to experience written content that leverages these powerful cognitive connections.

What it does

Memody transforms the reading experience by creating a synchronized audio-visual experience: Real-time text highlighting follows your natural reading pace, using a karaoke-style visualization Converts text into melodic patterns based on sentence structure, word importance, and semantic meaning Creates unique musical signatures for different types of content (articles, documentation, educational material) Offers customizable audio settings to match user preferences and content type Works seamlessly across any webpage through the browser extension

How we built it

JavaScript-based browser extension framework for cross-browser compatibility Text analysis engine to process sentence structure and time words to music(music.ai) LLM to generate music corresponding to text Interpretative layer LLM for simplifying dense text

Challenges we ran into

Sourcing an LLM to generate music corresponding to text Deciding on the optimal purpose of the application (enhancing learning and memorization with multi-modal learning vs. emphasis on interpreting the text into catchy tunes) challenges of matching natural sounding music to reading speed

Accomplishments we're proud of

Created a novel approach to enhancing reading comprehension through music Developed a text-to-music system that produces coherent, pleasant melodies Built a smooth, intuitive user interface that works across various websites without significantly impacting user performance

What we learned

the importance of the user experience in educational tools adjusting between performance and functionality, making tradeoffs The challenges of sourcing technology for cheap in a burgeoning field

What's next

Real-time text tracking system for accurate highlighting Enhance the tool specifically for people with ADHD and dyslexia A custom algorithm that further aligns text patterns with music Build analytics to track reading comprehension improvements Add support for different languages Enhance the tool specifically for people with ADHD and dyslexia A custom algorithm that further aligns text patterns with music Build analytics to track reading comprehension improvements Add support for different languages

Analysis

Compare with all teams

View

Metric

Figures cover GitHub contributors during the hackathon window. A co-authored commit counts in full for each author, so per-member totals add up to more than the whole-team figures.

Technology

Found in codeClaimed only
  • CSSIn code
  • HTMLIn code
  • JavaScriptIn code

3 of 3 appear in the indexed code.

AI coding agents

No AI coding agent signals were found in this repository.

Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.

Codebase size

Source size

16 KB

Source files

6

Counts recognized source files only; vendored directories, binaries and lockfiles are excluded, so this is smaller than the repository on disk.

0 stars