Dictation
Create Dictation Session
Create a Dictation session to transcribe spoken audio into text in real time
POST
cURL
Use this endpoint to create a session to transcribe spoken audio into text.
Refer to the Audio Dictation guide for more information.
Returns a
audio_config.audio_language supports English and Multilingual. If you omit audio_config, language defaults to English. Refer to Dictation basic usage guide for more information.201 Created status with the transcription_session_id that is used to identify the session for transcribing audio and ending the session.Authorizations
Suki access token (suki_token) from Login or Register. Expires after one hour.
Headers
Optional for standard partners.
Required for:
- Bearer authentication. Use the same
provider_idreturned by the Login or Register API. - Single Auth Token authentication. Include the same
provider_idon every request assdp_provider_id.
Example:
"provider-123"
Body
application/json
Optional transcription session ID and audio configuration. Suki generates an ID when omitted.
Response
Resource created successfully.
Response body for the /transcription/session/create endpoint
Unique identifier for the transcription session
Example:
"123dfg-456dfg-789dfg-012dfg"
Last modified on August 20, 2026
cURL