Inspiration

Student learning features a substantial amount of time sitting and reading content.

What it does

Turn pdfs into an engaging podcast between a guest and host. These simulate insightful conversations.

How we built it

Backend utilises Google Cloud: Gemini for scripts, Google Cloud: Text To Speech to generate a podcast from a pdf upload and Google Cloud Storage (GCS) to store files. PostgreSQL used to store metadata about what files exist in GCS.

Frontend uses a simple UX similar to Spotify for a familiar experience, with obvious sections for main functionalities.

Challenges we ran into

Connecting frontend and backend.

Accomplishments that we're proud of

Achieving programmatically alternating voices for a podcast script to simulate an engaging podcast. Successfully connecting frontend and backend.

What we learned

Docker is important.

What's next for Team SIT102: Luyu

Luyu can be improved by making the podcast voices more natural, can be done by modifying the existing implementation or waiting for Google's two-person voices to release. We plan to continue participating in hackathons.

Share this project:

Updates