Building AapdaMitra: An AI Disaster Response Voice Assistant for India with Murf Falcon & LiveKit
My journey through the 10 Days of Voice Agents – VoiceForBharat Edition challenge. Introduction 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…
During emergencies, clear and concise voice guidance can be critical for people's safety. However, typing on devices or searching online is difficult and time-consuming when people are panicked. To address this issue, the author created AapdaMitra, an AI-powered Disaster Response Voice Assistant tailored for India. This voice assistant uses natural language conversation to provide disaster safety guidance, weather information, user memory, human escalation, outbound voice calls, specialist agent handoffs, and call analytics dashboards.
Designed as part of the 10 Days of Voice Agents – VoiceForBharat Edition challenge, AapdaMitra combines Murf Falcon for text-to-speech, LiveKit Agents and LiveKit for real-time communication, Google Gemini as the large language model, and Deepgram for speech-to-text. The primary challenges faced during project development included designing effective prompts for Google Gemini to collect all necessary user data, integrating outbound SIP calling, and handling participant interactions.
By carefully structuring the workflow and troubleshooting technical issues, AapdaMitra was successfully built to prioritize user safety while preventing AI hallucinations.
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.
