VidAssembly

Transcribe, Summarise, Translate, Analyse Speakers, Extract Keywords and Slides

View Demo · Report Bug · Request Feature

👋🏻 Introducing VidAssembly

Tired of sitting through long and boring videos? Say hello to VidAssembly! 👋

Our cutting-edge deep learning technology powered by Assembly AI will revolutionize the way you consume video content. With VidAssembly, you can turn any long, boring video into bite-sized, engaging content.

Whether it's a one hour lecture or a 30-minute zoom meeting, VidAssembly can transcribe, summarise, detect and extract the important slides and keywords from the video, and even translate the content into other languages.

Say goodbye to boredom and hello to a better way to watch videos with VidAssembly!

🚀 Demo

Here is a quick demo of the app. We hope you enjoy it.

The Demo Link

Liked it? Please give a ⭐️ to VidAssembly.

🔥 Features

VidAssembly comes with a bundle of features already. You can do the followings with it,

• 📝 Transcribe videos using speech recognition
• 📃 Summarise content into short insightful pieces
• 🌐 Translate transcript to over 20 languages
• 💬 Analyse speakers during
• ❗ Extract important keywords from the video
• 🖼️ Extract important slides from the video

🏗️ App Architecture

Frontend

• React.js
• Tailwind CSS
• Deploy on GitHub pages

Backend

• Flask server
• Deploy on a GPU machine
• Relay to an Internet-facing VPS
• Nginx reverse proxy
• Cloudflare protection

Artificial Intelligence

• Assembly AI
• YOLOv7

Tools

• OpenCV
• yt-dlp
• ffmpeg

🏗️ Setting up VidAssembly for Backend Development

The application requires the command-line tool ffmpeg to be installed on your system, which is available from most package managers:

on Ubuntu or Debian

sudo apt update && sudo apt install ffmpeg

on Arch Linux

sudo pacman -S ffmpeg

on MacOS using Homebrew (https://brew.sh/)

brew install ffmpeg

on Windows using Chocolatey (https://chocolatey.org/)

choco install ffmpeg

on Windows using Scoop (https://scoop.sh/)

scoop install ffmpeg

Develop

## create an virtual environment
python3.10 -m venv venv
. ./venv/bin/activate

## install packages
pip install -U pip
pip install -U wheel
pip install -r requirements.txt

## download model weights
wget https://github.com/ztjhz/yolov7-slides-extraction/releases/download/v1.0/best.pt

## set API access key
export BAIDU_APP_ID=_BAIDU_APP_ID
export BAIDU_APP_KEY=_BAIDU_APP_KEY
export API_KEY=_ASSEMBLY_AI_API_KEY

## start the server
flask --app app run

Deploy

waitress-serve --host 127.0.0.1 --port 31346 app:app