We want to help amputees get access to exercises fit specifically for them. Each disability and amputation commonly comes with different problems and AI is a wonderful tool to accommodate for them and give personalized results so they can get fit. We will be asking the user for 14 questions about their disability and their diet to get a more accurate recommendation based on a multitude of studies and articles that recommend different tips to improve their lives. They can also speak further for dietary recommendations and get personalized exercises. This can further be expanded with insurance companies investing in these tools and more deep learning.

Assistants API and Trulens Hackathon

Ampufitness is an AI that gives specific recommendations to the amputees based on their unique physical disabilities. It asks 14 questions and tailors the AI to give the best recommendation possible.

AmpuFitness

OpenGPTs

Langchain

TruLens

TruEra

LlamaIndex

MongoDB

Agriculture remains a vital sector in many developing regions, but knowledge sharing and the adoption of modern practices are often hindered by language barriers. Farmers, especially in rural areas, struggle to access and comprehend information presented in languages unfamiliar to them, limiting their ability to learn about new crops, farming techniques, and equipment.
Our solution is an AI-driven image generation platform that empowers users to create vivid, detailed visuals by inputting text prompts in their local languages. By bridging the language gap, this tool allows farmers to visualize and understand complex agricultural concepts, facilitating knowledge exchange and accelerating the adoption of best practices.
Targeted primarily at smallholder farmers and agricultural communities in developing regions, our tool is designed to be intuitive and accessible, even for users with limited technological expertise.
A unique benefit of our platform is its ability to generate not only static images but also animated visualizations, making it easier to convey dynamic agricultural processes, such as planting techniques or machinery operations. Additionally, the generated visuals can be easily shared and disseminated through various channels, amplifying their impact on knowledge transfer and adoption.
Furthermore, our tool leverages the latest advancements in AI and natural language processing, ensuring that the generated visuals accurately capture the nuances and contextual meanings of the local language prompts. This level of precision is crucial in the agricultural domain, where even subtle differences in terminology can have significant implications for crop yields and farming practices.
By harnessing the power of AI and local languages, our image generation platform empowers farmers to break through linguistic barriers, fostering a more inclusive and sustainable agricultural ecosystem that benefits rural communities worldwide.


Textuary is an AI image generator. Input text descriptions of crops, farming practices, or equipment in your native language, and let advanced AI generate insightful visuals. Designed to bridge language barriers, share knowledge, and increase productivity

Team textuary

Empower your workflows with tailored AI models. Custom GPTs offer versatile solutions for personalized tasks and seamless integration. Create, customize, and share your GPTs effortlessly.

Custom GPTs

OpenAI is an AI research and deployment company

OpenAI

Stable Diffusion is a latent text-to-image diffusion model capable of generating stylized and photo-realistic images. It is pre-trained on a subset of of the LAION-5B dataset and the model can be run at home on a consumer grade graphics card so everyone can create stunning art within seconds.

Stable Diffusion

Explore Stability AI, the vanguard of open source generative AI, empowering global creativity and innovation

Stability AI

Textuary

This project uses the ffmpeg-python and faster-whisper libraries to create an application capable of extracting audio from an input video, transcribing the extracted audio, generating an English subtitle file based on transcription, translate the subtitles of this file into Yoruba using the Google Translate API and add it to a copy of the input video:
-Extract audio track from an input video
-Transcribes the audio track using the Whisper template
-Generates a subtitle file in SRT format
-Translates subtitles into a target language (default is Yoruba language)
-Adds translated subtitles to input video as soft or hard subtitles

This project generates a local language subtitle file from a video.

YesWeCan

Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.

Whisper

Generate-subtitle

Our project aims to preserve and promote local festivals and cultural events using cutting-edge AI technology. Users can input text or record audio describing their events in languages such as Yoruba, Fon, French, or English. The AI system transcribes and translates the input, generating detailed promotional posters with dynamic backgrounds and tailored social media content. The posters are visually compelling and culturally appropriate, enhancing visibility and engagement. By leveraging AI for content creation and translation, our platform bridges language gaps and empowers communities to share their heritage with a broader audience, fostering cultural preservation and celebration in an increasingly digital world.

Capture and promote local festivals using AI. Upload text or audio to generate detailed posters 

Dreamverse Frogs

Empower your projects with customizable language models, prompt precision, and extensive tool integration through OpenGPTs by LangChain.

Large language models (LLMs) have transformed the way we approach machine learning and artificial intelligence. These models are incredibly powerful, but their true potential lies in their ability to work in harmony with other sources of data and computation. This library has been developed to assist developers in building applications that combine LLMs with other technologies, allowing them to create truly intelligent and innovative products.

Explore Gemini, Google DeepMind's most advanced AI model, blending multimodality and high efficiency.

Gemini AI

Discover Alphabet Inc.'s gem: Google LLC! A global multi-tech marvel offering internet-focused services – search engines, online ads, cloud prowess, software savvy, and hardware innovation.

Google

Explore image generation capabilities with the cutting-edge DALL·E API.

DALL·E Image Generation API

Gishta Promotions

We've developed a comprehensive solution to address the challenges in tourism, particularly in the realm of eco-tourism, by harnessing the power of AI and linguistic diversity. Our innovative approach focuses on enhancing the visual representation of unique heritage sites through AI-generated visuals in local languages, thereby captivating visitors and fostering sustainable tourism practices. Moreover, we've created an AI application capable of enriching videos with subtitles, facilitating seamless communication across various local languages and other languages. This ensures that cultural narratives are effectively conveyed to a wider audience, promoting inclusivity and understanding. Additionally, our solution explores the creation of captivating images from audio and text in local languages, further enhancing accessibility and cultural representation in multimedia content. Through these features, we aim to revolutionize the tourism industry by providing immersive experiences that celebrate and preserve the richness of local heritage.
Website Demo Link : https://pixelam.vercel.app/

Introducing our groundbreaking eco-tourism solution powered by AI and linguistic diversity. We enhance heritage sites with AI-generated visuals in local languages, captivating visitors and promoting sustainable tourism.

Pixel

Pixelam

The operation has been meticulously simplified to ensure accessibility for all users. Upon accessing the application, users are prompted to input their preferences for different games and activities. Once selected, they can initiate the story generation process with a simple click on the "Generate a Story" button. The application then orchestrates a vibrant narrative complete with engaging visuals, meticulously crafted to be both coherent and easily understandable by children. Each scene is accompanied by a descriptive passage in Yoruba, enriching the cultural experience.
Intrigued by a particular scene? Users need only click on the "OK" button, triggering an immersive storytelling experience. A narrator adept in the nuances of Yoruba language and culture will gracefully unravel the tale, providing a deeper understanding and appreciation for the narrative's cultural significance. This seamless integration of visuals, language, and storytelling ensures an enriching journey through African culture for young minds.

Africa Story is a tool designed to generate visual narratives tailored for children. Its aim is to foster an appreciation for African culture among the youngest members of our society, who will in turn become ambassadors of our heritage and traditions.

RedTeam

Explore the cutting-edge capabilities of SDXL Turbo with real-time, high-fidelity text-to-image transformations.

AmpuFitness

Textuary

Generate-subtitle

Gishta Promotions

Pixelam

Africa story

Textuary

Generate-subtitle

Gishta Promotions

Pixelam

Africa story