Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.medera.info/llms.txt

Use this file to discover all available pages before exploring further.

This guide walks you through building a real-time ambient scribe — diarized capture, in-encounter SOAP drafting in the practice template, and EHR sync — on the Medera platform.

​
Architecture

┌───────────┐   ┌─────────────┐   ┌──────────────┐   ┌─────────────┐
│ Encounter │ → │  /streams   │ → │ Visit Scribe │ → │     EHR     │
│   audio   │   │ (WebSocket) │   │    Agent     │   │  (FHIR R4)  │
└───────────┘   └─────────────┘   └──────────────┘   └─────────────┘

​
Steps

1

Authenticate

Exchange your client credentials for an access token. See Authentication Quickstart.
2

Create an encounter

POST /api/sessions with the patient, provider, and visit type. The session ID anchors the transcript, note, and code suggestions.
3

Connect the audio stream

Open a WebSocket to wss://api.medera.ai/streams?session_id=...&token=... and stream PCM audio at 16 kHz. See Streams endpoint.
4

Receive transcript + note events

The stream emits transcript.partial, transcript.final, note.draft, and code.suggestion events. Render them as the clinician dictates.
5

Sign and post

After clinician sign-off, POST /api/clinical/notes/{id}/sign posts the structured note and code set to the configured EHR target via the integration adapter.

​
Best practices

  • Capture audio at 16 kHz 16-bit PCM. Higher rates work but waste bandwidth.
  • Use a dedicated lavalier or beamforming mic. See Microphone Devices.
  • Always require clinician sign-off before posting. Never auto-post to the EHR.
  • Use the transcript.span IDs to render the documentation anchor next to every code suggestion.

Streams endpoint

WebSocket schema and event reference.

Visit Scribe Agent

Agent-level documentation.

EHR Integrations

Connect Epic, Cerner, athenahealth, and more.

Encounter Coding

ICD-10 and CPT from clinical context.