Skip to main content
Eka’s medical scribe stack listens to a consultation or dictation and produces structured clinical documentation. It is built on Parrotlet-a, our medical ASR models for Indian English and Indian languages, trained on real clinical speech with its accents, code-mixing and drug vocabulary.

What it does

  • Transcribes medical speech in Indian English, Hindi, Marathi, Kannada, Telugu and more, including code-mixed doctor–patient conversation
  • Recognises medical entities — drug names, doses, conditions, procedures, lab tests — that general-purpose ASR gets wrong
  • Structures the transcript into clinical notes, prescriptions and EMR-ready records
  • Ships as a product — EkaScribe, an ambient AI scribe with SDKs and APIs
Model versions, language coverage and benchmark numbers change with each release; the current numbers are on the model cards and launch blogs below.

Read more

Models and datasets

Try it out