Hyperlink is a web-based python-generate software which dedicates to enhance the understanding of the text by providing a video for people to watch. Instead of reading boring text, the user can watch a video generated from the text. Based on Microsoft Azure Cognitive Services APIs, the software can generate a video based on the user's text input, which could be either a word, a phrase or a long paragraph. By analyzing each sentence in the text, our software will find the best matching pictures online with the help of Bing Image Search API, and then generate a video composed of these pictures and the sounds, based on the text, generated with the help of Bing Speech API.
The software will also potentially help children, people have the reading disorder, and essentially assist people to better understand the text online and raise their further interests in learning. We also apply Microsoft Azure VPS, which aims to generate a virtual server to host the web page. Moreover, Bing Web Search API creates a platform to search information from Bing through a python script. Therefore, generate the information for the Bing Speech API. Finally, we implement Text Analytic API to create a key information from each sentence which can be used to produce the keyword to search relatively matching pictures.
Firstly, install all dependencies by running "dependency.py". Then user shall type in the enter localhost:8293 in their browser and then enter the text they want to generate a video for. They need to specify the gender and language that they expect in the video. Recommend Linux/Ubuntu system. If you don’t have one, we also provide Mac version installation. Install all dependencies by running "dependency.py". The user will either use “M(ac)” or “U(nix)” to specify the system for installation.
- Microsoft Azure VPS
- Bing Image Search API - Add a variety of image search options to your app or website, from trending images to detailed insights.
- Bing Web Search API - Bring intelligent search to your apps and harness the ability to comb billions of web pages, images, videos, and news with a single API call.
- Bing Speech API - Convert audio to text, understand the intent, and convert text back to speech for natural responsiveness.
- Dingcheng Hu - [UC San Diego]
- Pengyu Chen - [UC San Diego]
- Wanhui Qiao - [UC San Diego]
- Renxu Hu - [UC San Diego]
- Zhibo Chen - [UC San Diego]
This project is licensed under the MIT License - see the LICENSE.md file for details
Azure and its APIs belong to Microsoft, Inc.