Patient Diagnostic Input
Phase 3 & 4
Audio Voice Input (STT)
Whisper / Deepgram
00:00
or attach audio file
No file selected
Medical Image / X-Ray / Rash Upload (Vision LLM)
GPT-4o / Llama Vision
Drag & drop medical image or browse
Supports PNG, JPG, WEBP (Max 25MB)
Patient Symptoms & Medical Notes
Doctor AI Response
Phase 1 & 2
Doctor Audio Response (TTS)
ElevenLabs / Edge-TTS
Diagnostic Evaluation & Advice
Record voice query, attach a medical image, or submit symptom notes to begin consultation.
LangGraph Agent Telemetry
Trace steps will display upon analysis.