Building AapdaMitra: An AI Disaster Response Voice Assistant for India with Murf Falcon & LiveKit

A developer built AapdaMitra, an AI-powered disaster response voice assistant for India, using Murf Falcon, LiveKit Agents, Google Gemini, and Deepgram. The assistant provides safety guidance, weather information, and human escalation through natural voice conversations, addressing challenges such as poor connectivity and user panic during emergencies. The project was developed for the 10 Days of Voice Agents – VoiceForBharat Edition challenge.

My journey through the 10 Days of Voice Agents – VoiceForBharat Edition challenge. Natural voice interaction can make technology more accessible during emergencies. In stressful situations, people often don't have time to type long messages or search through websites. They simply need clear guidance. To solve this problem, I built AapdaMitra, an AI-powered Disaster Response Voice Assistant designed for India. AapdaMitra helps users during emergencies such as floods, cyclones, earthquakes, fires, landslides, storms, and heatwaves through natural voice conversations. The project was built as part of the 10 Days of Voice Agents – VoiceForBharat Edition challenge using Murf Falcon, LiveKit Agents, Google Gemini, and Deepgram During disasters: People may panic. They may not be able to type. Internet connectivity may be poor. Quick spoken guidance can save valuable time. Voice is the most natural interface during emergencies. Meet AapdaMitra AapdaMitra is a conversational AI assistant that provides: Disaster safety guidance Weather information User memory Human escalation Outbound voice calls Specialist agent handoffs Call analytics dashboard The assistant always prioritizes user safety while avoiding hallucinations through carefully designed guardrails. Frontend Backend AI Models Database Other User Voice │ ▼ Deepgram Speech-to-Text │ ▼ Google Gemini │ ├── Memory Tool ├── Weather Tool ├── Escalation Tool ├── Analytics └── Specialist Agent │ ▼ Murf Falcon Text-to-Speech │ ▼ LiveKit │ ▼ User This project was far from straightforward. One major challenge was designing prompts that made Gemini collect all required user information before triggering tools like human escalation. Initially, the model skipped questions and called tools with incomplete data. The solution involved redesigning the workflow so the assistant gathered missing information one question at a time and only invoked the tool after every required field had been collected. Another challenge was integrating outbound SIP calling. Configuring LiveKit, Linphone, SIP trunks, and testing outbound calls required careful setup and troubleshooting. I also encountered issues with participant handling, webhook integration, session management, and UI synchronization before arriving at a stable implementation. Clone the repository. git clone <your-repository-url Install dependencies. uv sync Configure environment variables. LIVEKIT URL= LIVEKIT API KEY= LIVEKIT API SECRET= GOOGLE API KEY= DEEPGRAM API KEY= MURF API KEY= Run the backend. uv run python src/agent.py dev Start the frontend. npm install npm run dev Open the browser and begin a voice conversation. The 10 Days of Voice Agents – VoiceForBharat Edition challenge provided an excellent opportunity to explore real-time conversational AI. Building AapdaMitra helped me understand how voice, AI, and real-time communication can work together to create technology that has the potential to make a meaningful impact during emergencies. A big thank you to Murf AI for organizing this challenge and providing the opportunity to build with Murf Falcon, along with the powerful ecosystem around LiveKit.