> ## 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 APIs

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

The Dictation APIs enable partners to run 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 close cleanly.

These APIs are called from your servers and authenticated with a Suki Token (`sdp_suki_token`). Critically, Dictation returns transcript text for the session. It does not replace Ambient Session Management when you need a generated clinical note.

## Available endpoints

<Columns cols={3}>
  <Card title="Create Dictation Session" href="/api-reference/audio-transcription/create-session" arrow={true} icon="code">
    Create a Dictation session and receive a transcription session ID
  </Card>

  <Card title="Stream Dictation Session" href="/api-reference/audio-transcription/stream-transcription" arrow={true} icon="code">
    Stream audio over WebSocket and receive transcript frames
  </Card>

  <Card title="End Dictation Session" href="/api-reference/audio-transcription/end-session" arrow={true} icon="code">
    End the Dictation session when capture is finished
  </Card>
</Columns>

## Related guides

<Columns cols={2}>
  <Card title="Dictation Streaming" href="/documentation/how-to/audio-streaming/dictation-streaming" icon="book" cta="Learn more">
    Learn how to stream Dictation audio and receive transcript frames
  </Card>

  <Card title="Audio Dictation Overview" href="/documentation/concepts/dictation/dictation" icon="book" cta="Learn more">
    Learn how Dictation works and the different modes it supports
  </Card>

  <Card title="WebSocket Streaming Wire Format" href="/documentation/how-to/audio-streaming/websocket-streaming-wire-format" icon="book" cta="Learn more">
    Review outbound audio message framing for Dictation WebSockets
  </Card>

  <Card title="Read Dictation Transcript Frames" href="/documentation/how-to/audio-streaming/dictation-streaming-transcripts" icon="book" cta="Learn more">
    Learn how to parse inbound transcript frames from the Dictation WebSocket
  </Card>
</Columns>

## Common use cases

<Columns cols={2}>
  <Card title="Dictate into chart fields and scratchpads">
    Capture speech-to-text for the focused field or scratchpad without running the full ambient clinical note pipeline.
  </Card>

  <Card title="Correct ambient drafts in place">
    Let clinicians fix wording in a generated note with Dictation, then save the edited content in your existing chart workflow.
  </Card>

  <Card title="Stream transcripts on custom clients">
    Own audio capture on a backend or device gateway while your UI renders live transcript results for the clinician.
  </Card>

  <Card title="Support push-to-talk dictation">
    Keep one Dictation session available across multiple speech bursts until the clinician finishes the documentation task.
  </Card>
</Columns>