MediVision-Assistant

🩺 MediSight AI

Vision & Voice Assisted Medical AI (Educational Project)

MediSight AI is a multimodal AI medical assistant that analyzes user-uploaded images and spoken health concerns to generate concise, doctor-style responses.
The system integrates speech recognition, vision-language models, and text-to-speech to simulate a real-world medical consultation experience.

⚠️ This project is for educational and research purposes only and does not replace professional medical advice.

---

🚀 Features

• 🎤 Voice-based medical query input
• 🖼️ Image-based health analysis
• 🧠 Multimodal LLM reasoning
• 🔊 Spoken doctor-style responses
• 🌐 Gradio web interface
• ☁️ Deployable on Hugging Face Spaces

---

🧠 Tech Stack

• Frontend: Gradio
• Speech-to-Text: Whisper (via Groq)
• Multimodal LLM: Meta LLaMA 4 (Groq)
• Text-to-Speech: gTTS, ElevenLabs
• Backend: Python
• Deployment: Hugging Face Spaces

---

📁 Project Structure

artificial-doctor/ │ ├── app.py # Gradio application ├── Brain_of_doctor.py # Multimodal LLM (image + text) ├── voice_of_patient.py # Speech-to-text pipeline ├── voice_of_doctor.py # Text-to-speech pipeline │ ├── requirements.txt ├── README.md └── .gitignore