Your AI-Powered Video Summarization Tool

Introduction · Installation · Tech Stack · Implementation · Contributing · Snapshots

QuickVid is an open-sourced video summarization tool built with Whisper, GPT, LangChain & Supabase.

With QuickVid, you can save time and get the essence of any YouTube video with our intelligent summarization.

1. Clone the Repository

   git clone https://github.com/metaloozee/quickvid
   cd quickvid

2. Install Dependencies

   [pnpm | npm | yarn] install

3. Set Environment Variables

   NEXT_PUBLIC_SUPABASE_URL=your_supabase_url
   NEXT_PUBLIC_SUPABASE_ANON_KEY=your_supabase_anon_key
   

   replace your_supabase_url and your_supabase_anon_key with the actual values of your Supabase project.
4. Run the Application

   [pnpm | npm | yarn] run dev

   this will launch the application, and you can access it by visiting http://localhost:3000 in your web browser.

1. Clone the Repository

   git clone https://github.com/metaloozee/quickvid
   cd quickvid

2. Set Environment Variables

   NEXT_PUBLIC_SUPABASE_URL=your_supabase_url
   NEXT_PUBLIC_SUPABASE_ANON_KEY=your_supabase_anon_key
   

   replace your_supabase_url and your_supabase_anon_key with the actual values of your Supabase project.
3. Build the Docker Image

   docker build -t quickvid .

4. Run the Docker Container

   docker run -p 3000:3000 --env-file .env.local quickvid

   this will launch the Next.js application inside the Docker container, and you can access it by visiting http://localhost:3000 in your web browser.

• Next.js – Framework
• Typescript – Language
• Whisper - Speech-to-Text
• LangChain - AI Summarization Chain
• Supabase – Database & Storage
• shadcn/ui - UI Component Library
• Tailwind – CSS

QuickVid is built as a standard Next.js application with the shadcn/ui template kit. The following technologies and services are used:

ytdl-core is used to download the YouTube video as an audio file.

Supabase Storage is used as an Amazon S3 alternative to store and serve the audio files generated by ytdl-core.

OpenAI's Whisper is used to perform speech-to-text operation on the particular audio file.

LangChain is used to process the transcript using its Summarization Chain which summarizes a document by dividing it into small chunks.

We love our contributors! Here's how you can contribute:

• Open an issue if you believe you've encountered a bug.
• Make a pull request to add new features/make quality-of-life improvements/fix bugs.

• Ayan (@metaloozee)

QuickVid is open-sourced under the GNU General Public License Version 3 (GPLv3) or any later version. You can find it here