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
POST Create Dictation Session
Purpose: Create a Dictation session and receive a transcription session ID.
GET Stream Dictation Session
Purpose: Stream audio over WebSocket and receive transcript frames.
POST End Dictation Session
Purpose: End the Dictation session when capture is finished.
POST Rewrite Content
Purpose: Rewrite a selected span of clinical text with CONCISE, VERBOSE, or PATIENT_FRIENDLY.
Related guides
Dictation Streaming
Learn how to stream Dictation audio and receive transcript frames.
Rewrite Dictation Content
Rewrite selected text and replace the span in your UI.
Audio Dictation Overview
Learn how Dictation works and the different modes it supports.
Read Dictation Transcript Frames
Learn how to parse inbound transcript frames from the Dictation WebSocket.
Common use cases
Dictate into chart fields and scratchpads
Capture speech-to-text for the focused field or scratchpad without running the full ambient clinical note pipeline.
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.
Rewrite selected clinical text
After Dictation or other plain-text capture, let clinicians reshape a selection with Concise, Verbose, or Patient friendly, then write the result back in your UI.
Stream transcripts on custom clients
Own audio capture on a backend or device gateway while your UI renders live transcript results for the clinician.
Support push-to-talk dictation
Keep one Dictation session available across multiple speech bursts until the clinician finishes the documentation task.