Voice & Transcription (1.0.0)

Download OpenAPI specification:

Voice recordings, transcription processing and document management

Download a Clinical Document

Stream and download a document that was previously uploaded to Kana. Returns the file content directly for display or download in your application. Supports all document types stored via the document upload endpoint.

Use this when:

  • Displaying or downloading documents stored in Kana within your application
  • Allowing clinicians to retrieve documents they attached to client records

Input:

  • file_name (required): Name of the file to retrieve
  • file_url (required): Storage path returned by the upload endpoint

Returns: Streamed file content with appropriate Content-Type header

Authorizations:
cookieAuthbasicAuthNone

Responses

Upload and Process a Clinical Document

Upload clinical documents (PDFs, Word files, images) to Kana's secure storage and immediately extract their text content using Azure Document Intelligence. Extracted content is returned and can be used as context for AI note generation, clinical documentation, or chat queries.

Use this when:

  • You want to send referral letters, intake forms, or prior records to Kana
  • Building a document intake workflow where files are analyzed and stored
  • You need Kana's AI to incorporate external documents into clinical context

Supported file types: PDF, DOCX, images (JPEG, PNG, TIFF)

Input (multipart/form-data):

  • files (required): One or more documents to upload and process
  • userid (required): Client's Kana user ID
  • role (required): "User" or "Therapist"
  • feature (required): Feature context identifier (e.g. "TherapistNotes")

Returns: Array of objects with content (extracted text), file_name, and file_url for each uploaded document (HTTP 201)

Authorizations:
cookieAuthbasicAuthNone

Responses

Upload a Session Voice Recording

Upload an audio recording of a therapy session to Kana's secure cloud storage. Kana stores the recording and queues it for AI transcription and session summary generation. Recordings are organized by therapist, client, and date. Multiple audio chunks (e.g. from a segmented recording) can be uploaded; set is_last_blob=true on the final chunk to trigger downstream processing.

Use this when:

  • Your platform captures session audio and you want Kana to transcribe and summarize it
  • Building an integration where session recordings automatically flow into Kana
  • You need Kana to generate AI session notes from recorded audio

Input (multipart/form-data):

  • file (required): Audio file to upload
  • therapist_userid (required): Therapist's Kana user ID
  • therapist_clientid (required): Therapist-client relationship ID
  • session_id (required): Active session ID
  • is_last_blob (required): true if this is the final audio chunk
  • client_userid (optional): Client's Kana user ID
  • therapist_session_id (optional): Associated session ID

Returns: Record ID and upload status

Authorizations:
cookieAuthbasicAuthNone
Request Body schema:
filename
string or null <= 512 characters
userid
integer or null
is_processed
boolean or null
therapist_client_id
integer or null
create_timestamp
string or null <date-time>
update_timestamp
string or null <date-time>
session_id
string or null <= 255 characters
is_last_blob
boolean or null
therapist_session_id
integer or null

Responses

Request samples

Content type
{
  • "filename": "string",
  • "userid": 0,
  • "is_processed": true,
  • "therapist_client_id": 0,
  • "create_timestamp": "2019-08-24T14:15:22Z",
  • "update_timestamp": "2019-08-24T14:15:22Z",
  • "session_id": "string",
  • "is_last_blob": true,
  • "therapist_session_id": 0
}

Response samples

Content type
application/json
{
  • "id": 0,
  • "filename": "string",
  • "userid": 0,
  • "is_processed": true,
  • "therapist_client_id": 0,
  • "create_timestamp": "2019-08-24T14:15:22Z",
  • "update_timestamp": "2019-08-24T14:15:22Z",
  • "session_id": "string",
  • "is_last_blob": true,
  • "therapist_session_id": 0
}

Retrieve Session Transcript History for a Client

Retrieve the full history of session transcripts for a client, ordered by most recent first. Returns all transcript versions including revisions, giving a complete audit trail of what was transcribed across all sessions.

Use this when:

  • Building a session history timeline in your application
  • Auditing all transcription activity for a client
  • Reviewing how a client's session content has progressed over time

Input:

  • userid (required): The client's Kana user ID
  • therapist_clientid (required): The therapist-client relationship ID

Returns: Array of transcript history records ordered by most recent (HTTP 200). HTTP 204 if no history found.

Authorizations:
cookieAuthbasicAuthNone
Request Body schema:
required
transcript_summary
required
string
client_user_id
integer or null
therapist_user_id
integer or null
therapist_client_id
integer or null
date
required
string <date-time>
therapist_session_id
integer or null

Responses

Request samples

Content type
{
  • "transcript_summary": "string",
  • "client_user_id": 0,
  • "therapist_user_id": 0,
  • "therapist_client_id": 0,
  • "date": "2019-08-24T14:15:22Z",
  • "therapist_session_id": 0
}

Response samples

Content type
application/json
{
  • "id": 0,
  • "transcript_summary": "string",
  • "client_user_id": 0,
  • "therapist_user_id": 0,
  • "therapist_client_id": 0,
  • "date": "2019-08-24T14:15:22Z",
  • "therapist_session_id": 0
}

Transcribe a Session Recording

Trigger AI transcription of session audio recordings that were previously uploaded to Kana. Kana retrieves all audio files for the specified therapist-client-date combination, runs Azure Speech-to-Text transcription, and returns the transcribed text. Transcripts feed into Kana's AI pipeline for session summary and SOAP note generation.

Use this when:

  • You have uploaded session recordings and want Kana to transcribe them
  • Building an automated post-session workflow: record → transcribe → generate notes
  • You need raw transcripts from a session to display or process in your system

Input:

  • userid (required): Therapist's Kana user ID
  • therapist_clientid (required): Therapist-client relationship ID
  • date (required): Session date in YYYY-MM-DD format

Returns: Array of transcript text objects for all recordings on that date

Authorizations:
cookieAuthbasicAuthNone

Responses