> ## 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.

# Building Your Dictation Solution

> Dictation implementation guide

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 Medera STT + Medera STT with sub-second interim results, smart punctuation, and command parsing.

```javascript theme={"system"}
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](/multimodal/stt/commands).

## Drop-in web component

For React, Vue, or vanilla web apps, use the [Dictation Web Component](/sdks/dictation-component) — microphone management, push-to-talk, and editor wiring out of the box.

## Related

<CardGroup cols={2}>
  <Card title="Transcribe endpoint" href="/multimodal/stt/transcribe">
    Real-time stateless dictation.
  </Card>

  <Card title="Streams endpoint" href="/multimodal/stt/streams">
    Ambient + diarized encounter audio.
  </Card>

  <Card title="Commands" href="/multimodal/stt/commands">
    Voice command authoring.
  </Card>

  <Card title="Microphones" href="/multimodal/stt/microphones">
    Recommended hardware.
  </Card>
</CardGroup>