> ## Documentation Index
> Fetch the complete documentation index at: https://developer.suki.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Dictation API

> Create dictation sessions, stream audio for transcription, and end sessions

Use the dictation APIs when you need speech-to-text without the full ambient clinical note flow. You create a transcription session, open a WebSocket to stream audio, then end the session when capture is finished so resources can close cleanly.

## Usage scenarios

* You need speech-to-text without the full ambient clinical note flow.
* You want to create a transcription session, open a WebSocket to stream audio, then end the session when capture is finished so resources can close cleanly.

## How it works

The dictation APIs work in four steps:

<Steps>
  <Step title="Authenticate">
    Register the provider and obtain an **`sdp_suki_token`**. Refer to [Provider authentication](/api-reference/provider-authentication) and [Partner authentication](/documentation/partner-authentication).
  </Step>

  <Step title="Create a transcription session">
    Call [Create dictation session](/api-reference/audio-transcription/create-session) and save **`transcription_session_id`**.
  </Step>

  <Step title="Open a WebSocket to stream audio">
    Connect to [Stream audio to dictation session](/api-reference/audio-transcription/stream-transcription) when the session is **`READY`** or **`IDLE`**. Refer to [Dictation streaming](/documentation/dictation-streaming) for outbound audio messages and inbound transcript frames.
  </Step>

  <Step title="End the session when capture is finished">
    Call [End dictation session](/api-reference/audio-transcription/end-session) when capture is finished.
  </Step>
</Steps>

## Endpoints