I Built a Voice AI Assistant for Indian Farmers — My 10-Day Voice Agent Journey
What if a farmer could simply pick up a phone, speak naturally in Malayalam or English, and ask: “ What is today's market price? ” or “ It's going to rain tomorrow. Should I spray my crops today? ” or even: “ My crop is getting damaged. Can someone help me? ” No typing. No complicated menus. Just a conversation. That was the idea behind Farm & Field, the voice agent I built during the 10 Days of…
In an innovative project titled "Farm & Field," a voice assistant was developed to assist Indian farmers with agricultural inquiries. This AI-powered agent allows farmers to converse naturally in Malayalam, English, or Manglish, avoiding the need for typing or navigating through cumbersome menus. The goal was to create a user-friendly experience that simplified everyday agricultural concerns.
Farm & Field excels by offering several key features. Firstly, it can answer general farming questions, provide real-time weather updates, and retrieve current agricultural market prices. It also remembers returning users with their consent, enabling personalized interactions based on preferences like name, district, crops, land size, irrigation type, and language choice.
Rather than relying on guesswork, the agent utilizes dedicated tools for retrieving live data, such as market prices and weather forecasts. For complex issues like crop diseases or pest problems, the system escalates the conversation to a specialist agent, ensuring appropriate expertise is applied. Additionally, the agent can make outbound calls for important alerts, like weather warnings or market price changes.
To build this voice assistant, four main components are connected: Speech-to-Text (STT) using Deepgram, an LLM for conversation understanding powered by Google Gemini, Text-to-Speech (TTS) through Murf Falcon for fast and natural responses, and a real-time transport layer, LiveKit. The system also includes SQLite for user memory and call data management, and a dashboard for tracking call outcomes.
This project demonstrates the potential of voice AI in agriculture by making it accessible, efficient, and personalized for Indian farmers. The system's ability to handle multiple languages, access real-time tools, and escalate to specialists ensures comprehensive support for various farmer needs.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
