ORPHEUS
Medical speech recognition from Hamburg for dictation and consultation notes in hospitals and practices, operated in Germany.
What it does
ORPHEUS turns medical dictation into text in real time and adds punctuation itself, without spoken commands. Text appears wherever your cursor is, so it works directly in hospital and practice information systems, according to the vendor also under Citrix. A newer feature records the doctor-patient conversation, separates the speakers and turns it into a structured note based on a template. It also suggests ICD-10 codes, supports a custom vocabulary for names and in-house terms, reads text from screenshots and lets you share templates. There are clients for Windows and macOS plus apps for iOS and Android.
Who it suits
Doctors in practices, medical centres and hospitals, as well as nursing, therapy and administrative staff who document a lot. Practices can start without installing a server.
Data protection for businesses
Processing takes place in Germany: in the Standard plan on the STACKIT cloud, alternatively at GWDG or in your own data centre. Dictations are used for training only if you agree at first login; you can change this at any time under Settings › Privacy, and audio storage can be switched off entirely. The vendor does not mention a data processing agreement for ORPHEUS on its pages, so clarify this before use. Large organisations get an Enterprise plan with SSO and an SLA.
Limits
Only German and English so far. Running it on your own premises requires powerful GPU hardware. The accuracy figures come from the vendor’s own tests.