AI Medical Voicebot
March 2025
A multimodal AI-powered voicebot for healthcare that combines speech recognition, image analysis, and TTS for real-time medical insights.
Project Demo
Technologies Used
Project Links
Project Overview
This project features a voice-activated AI medical assistant that listens to voice input, transcribes it using Whisper-large-v3 via GROQ API, analyzes uploaded medical images with LLaMA-3.2 Vision, generates short professional diagnoses, and speaks the result using ElevenLabs or GTTS. Built in Python with a Gradio UI, it blends audio, vision, and NLP to create a seamless diagnostic experience.
Key Features
Voice Input & Transcription
Real-time transcription using Whisper-large-v3 via GROQ API.
Image-Based Diagnosis
Upload and analyze medical images using a powerful vision model.
Concise AI Insights
Generates short, professional responses tailored for healthcare.
Text-to-Speech Output
Converts AI responses into natural voice with ElevenLabs or GTTS.
Challenges
- •Combining multimodal AI (voice, vision, text) into a real-time flow
- •Ensuring quick and accurate transcriptions and image analysis
- •Integrating various APIs smoothly into a single UI
Key Learnings
- •Built a multimodal pipeline with real-time AI inference
- •Handled audio/image data and coordinated multiple services
- •Enhanced understanding of medical AI safety and clarity in generation
Project Gallery
Related Projects
You might also be interested in these projects.
Fragments Trails – Educational Q&A Platform
July 2025
A full-featured educational Q&A platform with AI moderation, personalized feeds, Trails, and admin/moderator control.
Scalable E-Commerce Platform
December 2024
A scalable full-stack e-commerce platform built with the MERN stack, TypeScript, Docker, Redis, Stripe, Firebase, Cloudinary, and more.
Agentic AI Researcher App
September 2025
An AI-powered research assistant that searches arXiv, reads papers, generates insights, and writes new research in LaTeX PDF format.