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.

Medera supports two dictation modes:
  • Stateless dictation — real-time transcription with command-and-control. Use the /transcribe endpoint.
  • Ambient dictation — long-form encounter audio with diarization. Use the /streams endpoint.

​
Stateless dictation

The /transcribe endpoint runs Whisper + Deepgram nova-2-medical with sub-second interim results, smart punctuation, and command parsing. 
import { MederaClient } from '@medera/sdk';

const client = new MederaClient({ accessToken });
const ws = await client.transcribe.connect({ language: 'en-US' });

ws.on('interim', (e) => console.log('Interim:', e.text));
ws.on('final', (e) => console.log('Final:', e.text));
ws.on('command', (e) => handleCommand(e.command, e.args));

const mic = await navigator.mediaDevices.getUserMedia({ audio: true });
ws.streamAudio(mic);

​
Commands

Dictation commands let the clinician control the editor by voice. See Dictation Commands.

​
Drop-in web component

For React, Vue, or vanilla web apps, use the Dictation Web Component — microphone management, push-to-talk, and editor wiring out of the box.

Transcribe endpoint

Real-time stateless dictation.

Streams endpoint

Ambient + diarized encounter audio.

Commands

Voice command authoring.

Microphones

Recommended hardware.