Voice Cloning Lite: Lightweight Text-to-Speech Web App
Built a lightweight, zero-cost text-to-speech application that converts text into downloadable audio across 60+ languages. Designed as a practical, free alternative to premium voice synthesis APIs—prioritizing accessibility and zero cloud costs over premium voice realism.
Engineering Decisions & Trade-offs:
Free-Tier Architecture: Integrated Google Text-to-Speech (gTTS) to eliminate API costs and ensure the app remains permanently free to use. This comes with a trade-off: voice output is functional and clear, but slightly robotic compared to premium paid alternatives (e.g., ElevenLabs, Coqui XTTS).
Multi-Language Support: Enabled text-to-speech across 60+ languages with adjustable speed control.
Audio Export: Implemented MP3 generation and download functionality, allowing users to save synthesized audio directly from the browser.
Production Deployment: Deployed on Streamlit Cloud with graceful error handling for text length limits and network issues.
Tech Stack: Python, Streamlit, gTTS, HTML/CSS.
0
35
AI Assistant: Agentic Web Search & Math Solver
Built an intelligent AI agent that autonomously decides which tool to use—web search or a calculator—based on the user's query. Unlike a standard chatbot, this system uses agentic reasoning to route questions to the appropriate backend.
Engineering Challenges Solved:
Agentic Decision-Making: Implemented LangChain to give the LLM the ability to reason about user intent and select between a real-time web search tool (Tavily) and a secure mathematical expression evaluator.
Real-Time Information Retrieval: Integrated the Tavily Search API to fetch live, up-to-date answers for questions about current events and general knowledge.
Secure Math Evaluation: Built a sandboxed expression parser to safely evaluate mathematical queries without risking code injection, supporting complex calculations.
Tool-Calling Architecture: Designed a modular pipeline that allows the agent to chain multiple tools together when needed for complex queries.
Tech Stack: Python, LangChain, Groq API (Llama 3.1), Tavily Search API, Streamlit.
0
78
AI Art Generator (Full-Stack Next.js Application)
Built and deployed a production-ready web application that generates images from text prompts using distributed GPU networks and multiple AI models.
Engineering Challenges Solved:
Distributed AI Networks: Integrated the AI Horde API to offload generation to a global volunteer GPU network, eliminating cloud GPU hosting costs while maintaining high availability.
Multi-Provider Architecture: Designed a modular provider system supporting Stable Diffusion 1.5, SDXL, and Flux models, allowing users to switch between models seamlessly.
Async Job Handling: Implemented robust asynchronous polling to handle queued jobs, status updates, and graceful degradation during peak network load.
Production Deployment: Built with Next.js 14 (App Router) and TypeScript, deployed on Vercel with CI/CD pipelines.
Tech Stack: Next.js 14, TypeScript, Tailwind CSS, AI Horde API, Replicate API.
0
65
PDF RAG Chatbot: Intelligent Document Q&A System
Built a production-ready Retrieval-Augmented Generation (RAG) system that allows users to upload PDF documents and ask complex questions, receiving accurate, context-aware answers instantly.
Engineering Challenges Solved:
Context Retrieval: Implemented a hybrid search system combining BM25 (keyword) and Vector Embeddings (semantic) using ChromaDB to ensure highly relevant document chunks are retrieved before passing them to the LLM.
LLM Integration: Connected the retrieval pipeline to Groq's Llama 3.1 API, achieving sub-second inference times while maintaining high answer relevancy.
Document Processing: Engineered a robust pipeline using pdfplumber to extract text from multi-page PDFs, with chunking and embedding strategies optimized for retrieval accuracy.
Tech Stack: Python, Flask, ChromaDB, Groq API (Llama 3.1), Sentence-Transformers, pdfplumber.
0
80
AI Music Generator with AudioLDM 2
Built a text-to-music generation web application that allows users to create custom 30-second audio clips based on genre and instrument prompts.
The Challenge: Running large audio diffusion models typically requires high-end cloud GPUs.
The Solution: I engineered this to run entirely on consumer hardware (GTX 1660 6GB) by implementing PyTorch optimizations including FP16 half-precision and memory-efficient inference.
Key Tech: Python, PyTorch, AudioLDM 2, Streamlit, Librosa (for waveform visualization).
Check out the live demo and GitHub repository linked below.
Github link :- https://github.com/Aikaksh-Singh-Routela
Live demo link :- https://ai-music-generator-eetwz9msem5mqtjptf9hol.streamlit.app/
0
63