How aiwithhassan/deploy-with-docker works
Project type and purpose
• This is a Python-based interactive AI audio application with a lightweight UI (Gradio).
• It implements a multi-phase conversational pipeline: capture patient voice → convert to text → generate doctor reply → synthesize doctor voice.
• The project can be run locally or containerized (Dockerfile present).
File structure
• Top-level Python scripts:
• brain_of_the_doctor.py – calls the LLM or rule engine to generate text replies
• voice_of_the_patient.py – captures/ingests mic input and runs speech-to-text
• voice_of_the_doctor.py – runs text-to-speech (gTTS/ElevenLabs)
• gradio_app.py – front-end server tying all phases into a web UI
• Configuration files:
• Dockerfile – container build instructions
• Pipfile / requirements.txt – Python dependencies
• Static assets:
• Various .mp3 files for testing TTS/ASR
• No separate “frontend” directory: UI lives in gradio_app.py
README for additional insights
• Lists external dependencies: FFmpeg, PortAudio – needed for audio I/O
• Describes four “phases” corresponding to the scripts above
• Shows both pipenv and pip/venv or conda install options