DEV
Sight beyond Sight
Our website enhances online content accessibility for the visually impaired with a cost-effective text-to-speech service using contemporary AI tools. Current market solutions lack necessary amenities and are costly. Working on the website: > once the website loads, the user inputs the URL of the website to be analyzed > this website is parsed using Beautiful Soup to gather the meaningful text content available on the page > this content is passed to the OpenAI text-davinci-003 model as a prompt and a summary is generated for the same > this summary is read out to the user using Azure in natural human tone > next, the website is again parsed using Beautiful Soup with the aim to download relevant images on that website > these images are then analyzed using Google Cloud Vision API and feature labels describing the prominent objects/contents of that image are generated > these labels are passed as a prompt to the OpenAI text-davinci-003 model and a meaningful sentence is generated which describes the images > the prompt already includes a set of sample labels and outputs that the model can use to understand the format of the desired output. > the image description generated in the above step is then read aloud using Azure. For Redis: Redis caches URL results for up to 3 hours, if URL exists in cache, output is displayed/read aloud. Otherwise, website is processed for new output. Results are removed after 3 hours for possible content changes. It allows for fast data access making it suitable for high performance use cases. For voice control: > using space bar, user can ask queries regarding summary through available chatbot > above query is converted to text via speech recognition library of python > this text and the summary are given to the OpenAI text-davinci-003 model as a prompt and the query is resolved > the result is spoken out and if speech unrecognized, an error message stating to retry is read aloud
Category tags:
"Great job on developing a website that enhances online content accessibility for visually impaired users with a cost-effective text-to-speech service using contemporary AI tools. Your approach of parsing the website to gather meaningful text content and generating a summary using OpenAI's text-davinci-003 model is a smart and efficient way to provide important information to users. I also appreciate the feature of downloading relevant images from the website and generating meaningful image descriptions using Google Cloud Vision API and OpenAI's text-davinci-003 model. This feature will greatly enhance the user experience for visually impaired users and make the website more accessible. Using Redis to cache URL results for up to 3 hours is a great way to improve the website's performance and provide fast data access for high performance use cases. I also like the voice control feature that allows users to ask queries regarding the summary through a chatbot, which is a user-friendly feature for those who prefer voice commands. Overall, your project shows great potential to provide a valuable service to visually impaired users and is a great example of using contemporary AI tools to enhance website accessibility. Keep up the good work!"
Pawel Czech
Co-founder/Partner
"Great idea that can go two ways - towards helping the visually impaired or summarizing and reading aloud articles - personally I would love to be able to voice command a website such as this to go through all the main news articles on certain sites and read aloud their summary to me when I'm driving or commuting. My only concern that as a product this would be difficult to market and sell."
Alek Jankowski
Operations and Partner Manager
"You've tackled a real-life problem and made a great solution for it! The demo is working just fine, but when explaining the technologies that'd been used, I'd love to see a simpler architecture. Other than that, you guys did a good job!"
Dimitrije Pesic
Student
"amazing, you did it guys. i really like the originality of idea! keep going!"
Ibrohim Abdivokhidov
Ai generated Not real
"Your website appears to be an innovative and useful solution to enhance online content accessibility for the visually impaired. Your use of contemporary AI tools, such as OpenAI and Google Cloud Vision API, to generate summaries and image descriptions is impressive. Additionally, your implementation of Redis for fast data access and voice control through a chatbot adds value to your product. Overall, your project has the potential to make a positive impact on the lives of many individuals"
Theodoros Ampas
Technical Mentor
For Innovators & Creators