Building Dukaan Sathi: An AI Voice Assistant for India's Kirana Stores

A developer built Dukaan Sathi, an AI voice assistant for India's Kirana stores, in nine days as part of the Voice for Bharat Challenge. The multi-agent system handles inventory, escalations, and speaks in Hindi, using prompt engineering to ensure proper Devanagari script for natural pronunciation. The project leverages LiveKit and Murf AI and is open-sourced on GitHub.

Over the past 9 days, I took on the Voice for Bharat Challenge to build an AI Voice Agent tailored for India. The result? Dukaan Sathi , a fully functional voice assistant designed specifically for local Kirana store owners dukaandars . Here is the story of how Dukaan Sathi evolved from a simple starter template into a multi-agent powerhouse capable of managing inventory, handling escalations, and speaking in authentic, pure Hindi. India runs on Kirana stores. Dukaandars are incredibly busy people, often juggling inventory, customer queries, and billing all at once. They don’t have the time to sit at a laptop and type data into complicated software. Why voice? Voice is the most natural, frictionless interface. I wanted a Dukaandar to be able to just speak to their phone: "Mere paas kitna chawal bacha hai?" How much rice do I have left? and get an instant, helpful response. Dukaan Sathi is that solution. It is a helpful, polite, and intelligent voice agent that acts as a digital assistant for the store. Dukaan Sathi isn't just a basic chatbot with text-to-speech bolted on. It's a complete, intelligent system. Here are the highlights of what I built: create escalation tool that saves a transcript and logs a ticket for the human owner to review.Pretending everything worked perfectly on the first try wouldn't be helpful Here are some hurdles I faced and how I solved them: The Problem: LLMs naturally default to writing Hindi in the Latin alphabet Hinglish because that's how a lot of their training data looks. However, when you feed Romanized Hindi into an Indian Text-to-Speech engine, the pronunciation often breaks down or sounds unnatural. The Solution: Heavy prompt engineering. I had to explicitly instruct the agent: "Always write every language in its own native script. Hindi - Devanagari नमस्ते , never romanized." This instantly fixed the pronunciation issues. Want to build your own version of Dukaan Sathi? It's easier than you think. You need four main components: .env.local frontend and .env backend file. uv run src/agent.py dev in your terminal. npm run dev in your terminal. localhost:3000 , click connect, and start talking You can write a custom SYSTEM PROMPT in agent.py to give your agent any personality you want.This 10-day challenge proved that voice AI is no longer a futuristic concept—it is accessible, buildable, and ready to solve real-world problems in India today. Thanks to LiveKit and Murf AI for providing the incredible tools that made this possible Want to see the code behind Dukaan Sathi? Check out the full source code for my 10-day journey on GitHub here: https://github.com/sanyamkansal/AI-Voice-Agent https://github.com/sanyamkansal/AI-Voice-Agent