Observed Signal · Aug 15, 2026 · Technical Release · Source: DEV Community · Impact: 2/5 · Sentiment: Positive
10-Day Voice Agent Build for Local Indian Store
A developer built a production-oriented voice assistant for a local Indian grocery/general store as part of a 10-day challenge (VoiceForBharat). The project implements a real-time voice pipeline combining Deepgram speech-to-text, Google Gemini LLM, Murf Falcon text-to-speech, and LiveKit for audio transport. Features included multilingual (English/Hindi/Hinglish) handling, caller memory (SQLite), safety guardrails, specialist handoffs for returns/refunds, outbound SIP calling via LiveKit, and call analytics exposed through a FastAPI backend. The complete source code is published on GitHub (Codehunter0009/murf-livekit-starter).
Provides a practical, production-oriented blueprint for multilingual voice agents with memory, specialist handoffs, SIP outbound calls, and analytics—useful reference for teams building conversational CX systems but not an industry-shifting platform announcement.
Track Deepgram Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your Polaris7 workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- The author built a voice assistant for a local Indian grocery/general store during a 10-day challenge called 10 Days of Voice Agents — VoiceForBharat Edition.
- The voice pipeline uses Deepgram for speech-to-text, Google Gemini as the LLM, Murf Falcon for text-to-speech, and LiveKit for real-time audio transport.
- The system supports English, Hindi, and Hinglish-style conversations and switches TTS locale between en-IN and hi-IN.
- Caller memory is implemented using SQLite with two tools: lookup_caller() and save_caller_memory(); the agent asks permission before saving preferences.
- The project includes outbound SIP phone calls using LiveKit, call tracking/analytics via a FastAPI backend, and the source code is available at GitHub: Codehunter0009/murf-livekit-starter.
Connected Companies & Entities
4 Entities mapped“Deepgram Nova-3 handles speech recognition.”
“Google Gemini handles language understanding and response generation.”
“Murf Falcon, using an Indian English voice, handles text-to-speech.”
“My project is available publicly on GitHub: Codehunter0009/murf-livekit-starter”
Ontology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Voice AI Assistant for Indian Farmers Built in 10 Days
A developer built "Farm & Field," a voice AI assistant for Indian farmers during the 10 Days of Voice Agents — VoiceForBharat Edition by Murf AI. The system integrates Speech-to-Text, an LLM, Text-to-Speech, and real-time transport (Deepgram, Google Gemini, Murf Falcon, LiveKit) with SQLite-backed memory, weather and market-price tools, human escalation, a specialist crop agent, outbound calling via LiveKit SIP, and call analytics. The agent supports Malayalam, English, and Manglish, requests consent before storing memory, and hands off to humans or specialists when appropriate. The project code is available on GitHub.
Bharat Buddy: 10-Day Voice AI Tutor Build
A developer built "Bharat Buddy," a multilingual voice-first AI tutor during the "10 Days of Voice Agents — VoiceForBharat Edition." The project integrates real-time audio via LiveKit, LLM reasoning, and Murf Falcon TTS to support Hindi, English and Hinglish. Features include user memory, tool calling, AI-initiated outbound calls, human escalation, specialist agent handoffs (e.g., a Maths Practice Specialist), and a simple call-analytics dashboard backed by SQLite. The author documents technical challenges (function-calling schema mismatches, secret management) and publishes the project repository on GitHub.
Developer Builds Multilingual AI Voice Agent 'Sadie'
A developer, Ayush Shinde, built Sadie — a multilingual AI voice agent — during the "10 Days of AI Voice Agents — #VoiceForBharat Edition" challenge. Over ten days he implemented real-time voice conversations, Hindi-English code-mixing support, persistent (permissioned) memory, tool integration, outbound phone calling via SIP, human escalation via Discord webhooks, an analytics dashboard, and multi-agent specialist handoffs (grammar, maths, full-stack). The system integrates LiveKit for real-time transport, Deepgram for STT, Google Gemini as the LLM brain, and Murf Falcon for TTS, with SQLite for memory and Next.js/Chart.js for analytics. The post documents architecture, implementation details, encountered bugs (telephony SIP encryption, logging issues, import paths), and instructions to run the public repository and demo.
Receive all future signals for Deepgram & competitors in your briefing
Never miss material M&A deals, leadership changes, account wins, or product rollouts. Polaris7 monitors 20,000+ primary sources 24/7, delivering verified telemetry directly into your executive briefing.