🦥 Slothify: You Relax, AI Handles the Boring Bits" to highlight your core tagline directly. Alternatively

1. Project Introduction

🦥 Slothify — AI That Does the Boring Work
Slothify is a cozy, minimal, AI-powered productivity web application built for the Hacktoberfest 2026 DEV Challenge. It helps students, professionals, and anyone overwhelmed by information save time by turning long, complicated text into short, actionable formats—and optionally reading it aloud.

2. Problem Statement

Processing long text is tedious and drains mental energy. Whether it is reading a dense 10-page study guide, parsing a convoluted college email for deadlines, or trying to understand a complicated article, users waste time doing the "boring bits." Slothify solves this by acting as a lazy little helper that handles the heavy lifting, allowing users to reduce their mental effort and get their time back.

3. Features

• ✨ Summarize: Condenses long text into a quick, readable overview.
• 📌 Key Points: Extracts essential information and bulleted details.
• ✅ Make a Checklist: Converts paragraphs into actionable tasks with dates and requirements.
• 💡 Simplify: Explains complicated text in simple, accessible language.
• 🔊 Listen: Generates high-quality voice narration of the AI result.

4. Demo

5. GitHub Repository & Setup Instructions

Repository: : https://github.com/AdibaNaushad/slothify.git

AdibaNaushad / slothify

🦥 Slothify — AI That Does the Boring Work

You relax. AI handles the boring bits.

Slothify is a cozy, AI-powered productivity workspace built for the Hacktoberfest 2026 DEV Challenge. It helps people save time by turning long, complicated text into short, actionable information—and optionally reading it aloud.

Reading dense college emails, 10-page study notes, or complicated articles is tedious. Slothify automates this process using a clean "Cozy Pastel Productivity" interface and open-weight AI, allowing users to reduce their mental effort and get their time back.

✨ Features

• ✨ Summarize: Condenses long text into a quick overview.
• 📌 Key Points: Extracts essential information and details.
• ✅ Make a Checklist: Converts paragraphs into actionable tasks.
• 💡 Simplify: Explains complicated text in simple, accessible language.
• 🔊 Listen: Reads the AI-generated result aloud using text-to-speech.

⚙️ How It Works

Component	Technology	Functionality
Frontend	React & Tailwind CSS	Provides the responsive, minimal UI and

…

View on GitHub

Setup Instructions:

1. Set up Local AI (Gemma): Install Ollama and run ollama pull gemma:2b in your terminal.
2. Set up the Backend:
3. Navigate to the backend folder and create a virtual environment (python -m venv venv).
4. Install dependencies: pip install fastapi uvicorn httpx pydantic python-dotenv.
5. Create a .env file and add your key: ELEVENLABS_API_KEY=your_key_here.

6. Start the server: uvicorn main:app --reload.

7. Set up the Frontend:

8. Navigate to the frontend folder.

9. Run npm install, then start the React app with npm run dev.

6. Technical Explanation

The architecture relies on a decoupled frontend and backend to seamlessly connect local AI processing with cloud-based voice generation.

Component	Technology	Functionality
Frontend	React & Tailwind CSS	Provides the responsive "Cozy Pastel Productivity" UI and manages state.
Backend	Python & FastAPI	Acts as the API bridge, validating inputs and routing them to the correct AI services.
AI Brain	Google Gemma (via Ollama)	Runs locally on the user's hardware to process text and generate tailored transformations.
Voice Engine	ElevenLabs API	Converts the Gemma-generated text into natural-sounding spoken audio.

7. Open Innovation Explanation (Hacktoberfest Categories)

Why Local Inference Matters
Slothify champions open-source by processing all text locally. Once the Gemma model is downloaded, the core text-transformation features operate without internet access. This guarantees absolute data privacy—sensitive study notes or personal emails never leave the user's computer. It also eliminates the recurring API costs associated with hosted language models, giving users full control over their computing resources.

🏆 Best Use of Gemma
Gemma is the central intelligence of this application. Served locally through Ollama, this open-weight model takes a single user input and transforms it dynamically based on precise backend prompting. Whether the user needs a bulleted list, a simplified explanation, or a checklist, Gemma handles the local processing efficiently without relying on third-party cloud LLMs.

🏆 Best Use of ElevenLabs
Slothify gives its open-source AI a voice using the ElevenLabs text-to-speech API. By allowing users to click "Listen," ElevenLabs generates natural-sounding narration for the AI's response. This makes the application significantly more accessible and convenient, transforming a tedious reading task into a passive listening experience.