AI-Driven Bilingual Voice Chatbot
S. Manimala · International Journal for Research in Applied Science and Engineering Technology · 2025
This project proposes an AI-driven, bilingual voice- enabled health chatbot that aims to enhance healthcare access in Karnataka’s rural and semi-urban zones. The system was initially developed with a fine-tuned GPT-2 model; however, it generated unpredictable and sometimes unrelated answers, particularly for advanced or bilingual inputs. To address these constraints, the model was substituted with Mistral LLM through integration on LangChain, allowing Retrieval-Augmented Generation (RAG) to generate more precise and context-specific responses from a carefully curated health QA dataset. Supporting both Kannada and English languages, voice interaction in real time, and a friendly Gradio interface, the chatbot offers inclusive, voice-to- voice health support customized for those with low literacy and restricted digital exposure