Building SpeakEasy AI: A Multilingual Voice Agent for Bharat

A developer built SpeakEasy AI, a multilingual voice-based AI assistant for the Murf AI Voice for Bharat Challenge, designed to help users practice English through natural conversations. The agent supports English, Hindi, and Hinglish, and includes features like conversational routing and a call analytics dashboard. The project highlights the importance of integrating speech-to-text, LLMs, and text-to-speech to create a complete voice experience.

Voice AI is becoming more accessible, but language and accessibility still remain important challenges for many users in India. As part of the Murf AI Voice for Bharat Challenge, I built SpeakEasy AI — a voice-based AI assistant designed to help users practice English through natural conversations. SpeakEasy AI is a conversational voice agent that allows users to speak naturally and receive AI-generated voice responses. The idea is simple: Speak naturally. Practice confidently. Improve one conversation at a time. The agent is designed around everyday English practice and supports English, Hindi, and Hinglish interactions. The project uses: The main goal was to make the interaction feel like a real conversation rather than a traditional chatbot. Users can start a voice conversation, speak naturally, and receive spoken responses from the AI agent. I also integrated a friendly female voice to make the experience more natural and approachable. One of the important parts of the project is handling different ways users communicate. For example, a user can switch between: This makes the experience more comfortable for users who may not be completely confident speaking English. I also experimented with conversational routing. For example, when a user asked for help with a mathematics problem, the main assistant could route the conversation toward a dedicated maths practice specialist. This makes the architecture more flexible because different specialists can handle different tasks. Another feature I implemented was a simple call analytics dashboard. The dashboard tracks: This provides a basic view of how the voice agent is performing. Building SpeakEasy AI helped me understand that a voice agent is much more than simply connecting speech-to-text with an LLM. Important parts include: The biggest learning for me was understanding how different AI components work together to create a complete voice experience. India has a huge diversity of languages and communication styles. Voice interfaces can make AI more accessible to people who may find traditional text-based interfaces difficult or less natural. With better multilingual support and localized voice experiences, conversational AI can become much more useful for everyday learning and communication. I plan to continue improving SpeakEasy AI by working on: This project has been a great hands-on experience in building production-oriented AI voice applications. Thanks to the Murf AI Voice for Bharat Challenge for providing the opportunity to explore voice AI more deeply.