Skip to content

tfrank11/brainrot-gpt-server

Repository files navigation

BrainRot GPT (Backend)

Turn PDFs into short form, digestible videos. Perfect if you have a sub-30 second attention span.

Live Site

Technology Stack

Python FastAPI Supabase Deepgram ElevenLabs OpenAI Heroku

Features

  1. Upload PDF: Users can upload a PDF document through the interface.
  2. Processing: The backend processes the PDF to extract text and generate a summary using OpenAI's GPT-4o-mini.
  3. Audio Generation: A voiceover is created based on the summary using ElevenLabs. This is the familiar TikTok voice.
  4. Video Creation: The application combines the audio with a source video using MoviePy, adding text overlays for captions.
  5. Download: Users can download the final video once processing is complete.

Key Services/Libraries Used

  • Supabase: For authentication and database.
  • OpenAI: For generating summaries from the extracted text.
  • ElevenLabs: For creating voiceovers based on the summary.
  • Deepgram: For transcribing the audio and getting timestamps for each word.
  • MoviePy: For video processing, including combining audio with a source video and adding text overlays.

Also See

Brainrot GPT Web

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published