You know the words matter. You just have not said them out loud yet.
Tomorrow you explain a procedure, walk someone through discharge plans, or open a first assessment. The facts are in your notes. What you do not have is a dry run where the stakes are low and someone tells you what landed and what did not.
The app is a local rehearsal room for that moment.
Say it once. Hear what worked.
What you get
- Named practice scenarios. Work through initial patient assessments, procedure explanations, and discharge instructions built into the project.
- Type or speak your answer. Use text input or voice input with transcription, then run analysis when you are ready.
- Feedback on four dimensions. Scores and suggestions cover medical accuracy, communication clarity, empathy and patient care, and completeness of information.
- A trail of attempts. All interactions are saved for review and improvement tracking so you can compare wording over time.
- Free and open source. MIT licensed, with setup documented on GitHub.
Picture your Thursday
For example, you pick a scenario from the sidebar, read the patient situation, and record a short voice answer. You stop recording, check the transcription, run analysis, and read how clear and complete your instructions sounded. You try again with simpler language before clinic.
Ready to try it?
- Get it on GitHub for clone, environment setup, and running the local web app. You supply a Google AI API key as shown in the repository.











