"Qissa Sunao" - an Urdu storytelling app revolutionizing the narrative experience! Harnessing voice model and dynamic illustration generation, users craft personalized audio-illustrated books. Choose your preferred voice, select a story from our collection, or create your own masterpiece. Watch as related illustrations dynamically complement the narration, creating a captivating journey through emotionally rich Urdu tales. Dive into storytelling like never before with "Qissa Sunao.
Objectives
An Immersive and accessible platform for preserving Urdu Storytelling heritage by combining Urdu Voice Model and Image Generation in an Audio-Illustrated book format.
Socio-Economic Benefit
1. Cultural Preservation and Promotion:
By preserving and promoting Urdu literature and storytelling traditions, especially in the digital age, the app contributes to maintaining cultural identity and heritage. This fosters a sense of pride and connection among Urdu-speaking communities, both locally and globally.
2. Increased Accessibility:
The accessibility features provided by the app, such as voice for those with reading difficulties or disabilities, ensure that a wider audience can access and enjoy Urdu literature. This inclusivity contributes to social equity and empowers individuals who may face barriers to traditional forms of literacy.
3. Economic Opportunities:
The app may stimulate economic activity by providing a platform for creators to monetize their content, leading to the growth of a digital content economy centered around Urdu storytelling.
4. Educational Enhancement:
The app can serve as a valuable educational resource, supporting language learning and literacy development among Urdu speakers of all ages. By providing engaging and interactive content, the app enhances learning outcomes and facilitates lifelong learning, which is essential for socio-economic advancement.
5. Innovation and Technological Advancement:
The integration of AI technologies fosters innovation and drives technological advancement in the field of digital storytelling. This not only benefits the app itself but also contributes to advancements in AI and multimedia technology more broadly.
Methodologies
Requirement Analysis:
In our initial phase, we conducted thorough research and user persona development to gain insights into our target audience's demographics, preferences, and expectations. We gathered valuable insights that informed the definition of features and functionalities, ensuring alignment with user needs.
Technology Selection:
After careful evaluation, we opted for React for front-end development, Node.js for backend, and Python FastAPI for API development. For voice model, we selected Tacotron and the vocoder for their effectiveness in synthesizing natural voices.
Database Design and Dataset Preparation:
We carefully designed the database schema to efficiently store and manage data related to user profiles, stories, and multimedia content. Additionally, we prepared a comprehensive dataset for training Tacotron, consisting of diverse Urdu speech recordings sourced from various sources. This dataset was meticulously curated and preprocessed to ensure optimal training performance and model accuracy.
Voice Model training:
Our implementation of voice technology involved leveraging state-of-the-art AI models like Tacotron and the vocoder. Through extensive training on a diverse dataset of Urdu speech recordings, we achieved a high level of naturalness and expressiveness in voice synthesis, significantly enhancing the immersive storytelling experience for our users.
Image Generation:
We employed cutting-edge image generation techniques, utilizing platforms like Leonardo, to generate visually stunning illustrations that complemented our audio narration seamlessly. Through creative exploration and experimentation, we crafted dynamic visuals that captivated our audience's imagination and enriched the storytelling experience.
App Development:
During the development phase, our focus was on creating a user-centric interface (UI) and an intuitive user experience (UX) for our storytelling app. We implemented features such as seamless story browsing and customizable user preferences using React for front-end development. Node.js was used for backend development to ensure smooth data flow and interaction, resulting in a cohesive and engaging experience for our users.
Testing and Iteration:
We conducted rigorous testing throughout the development cycle to identify and address any technical issues or usability concerns. Through iterative refinement, we enhanced the functionality, performance, and overall user satisfaction of our app, ensuring a seamless experience for our users.
Maintenance:
We continuously monitor performance, promptly resolve technical issues, and optimize our app to ensure its relevance, engagement, and accessibility to our users.
Outcome
The Successful development of the Qissa Sunao app on both iOS and Android platforms ensures widespread accessibility for users, catering to diverse preferences. Through immersive storytelling experiences, users can delve into captivating narratives, with AI-generated voices breathing life into characters and dynamic illustrations enriching their engagement with Urdu literature and culture. Offering personalization options directly from their mobile devices, users can select preferred voices and customize text to tailor their storytelling experience. Seamless integration with mobile device functionalities, including notifications, further enhances user interaction and engagement with the captivating content, ensuring a truly immersive and interactive experience for all users.
