RecipeXtractor

Inspiration

Nowadays, there are so many nice cafes and comfort food is everywhere—but it’s often expensive. We wanted to make it easy for anyone to enjoy great meals at home without spending hours searching. Instead of watching long videos to figure out ingredients and steps, RecipeXtractor gives you a clear grocery list, exact quantities, and instructions just minutes after you paste a YouTube link. Cooking becomes easy, fast, and fun—so you can spend more time enjoying your food.

What it does

RecipeXtractor takes a YouTube recipe video link, extracts the transcript and instructions, and generates a complete grocery list with quantities. It summarizes all the information clearly, so you don’t have to watch hours of video or guess what to buy. You can start cooking within minutes.

How we built it

We built the Android app in Kotlin and the backend server using Flask. The backend runs locally for now and uses Whisper for audio transcription and Gemini for summarization and context awareness. The workflow is: Paste YouTube link in the app Backend downloads audio Whisper generates transcript Gemini summarizes Grocery list + step-by-step instructions are sent back to the app.

Challenges we ran into

The biggest challenge was getting Whisper and Gemini to work together smoothly. Initially, we tried using YouTube transcripts directly, but many videos block access. Switching to Whisper for audio transcription solved that, but integration and timing issues took effort to debug.

Accomplishments that we're proud of

We built something meaningful, functional, and really easy to use. Unlike Instagram or other food apps that just show you pictures, RecipeXtractor actually helps you cook. The grocery list and summarized steps are ready in minutes, making cooking fast and stress-free.

What we learned

We learned a lot about audio transcription, AI summarization, and backend–frontend communication. Beyond the technical side, we realized the importance of giving users actionable results quickly, instead of hours of raw video content.

What's next for RecipeXtractor

Next, we want to add translation support for recipes in multiple languages. We also plan to use AI prompts to suggest ingredient alternatives for allergies, dietary restrictions, or substitutions. Eventually, the app could become a universal cooking companion for cuisines around the world.

Built With

• android-studio
• flask
• gemini
• kotlin
• localserver
• python
• whisper
• ytdls