POST
/
interactions
/
{id}
/
transcripts
curl --request POST \
  --url https://api.{environment}.corti.app/v2/interactions/{id}/transcripts/ \
  --header 'Content-Type: application/json' \
  --data '{
  "recordingId": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "primaryLanguage": "<string>",
  "isDictation": true,
  "isMultichannel": true,
  "diarize": true,
  "participants": [
    {
      "channel": 123,
      "role": "doctor"
    }
  ],
  "modelName": "<string>"
}'
{
  "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "metadata": {
    "participantsRoles": [
      {
        "channel": 123,
        "role": "doctor"
      }
    ]
  },
  "transcripts": [
    {
      "channel": 123,
      "participant": 123,
      "speakerId": 123,
      "text": "<string>",
      "start": 123,
      "end": 123
    }
  ]
}

Headers

​
Tenant-Name
string

Identifies a distinct entity within Corti's multi-tenant system. Ensures correct routing and authentication of the request.

Example:

"copiloteu"

Path Parameters

​
id
string
required

The unique identifier of the interaction for which the transcript is created. Must be a valid UUID.

Body

application/json
​
recordingId
string
required

The unique identifier for the recording.

​
primaryLanguage
string
required

The primary spoken language of the recording. Check https://docs.corti.ai/about/languages for more.

​
modelName
string
required

Can be "base", "enhanced", "premier". By default, only the highest tier is accessible. Check https://docs.corti.ai/about/languages for more.

​
isDictation
boolean

Indicates whether spoken dictation commands should be converted to punctuation (e.g., 'comma' → ',').

​
isMultichannel
boolean

If true, each audio channel is transcribed separately.

​
diarize
boolean

If true, separates speakers within an audio channel returning incrementing ids for transcript segments.

​
participants
object[]

An array of participants, each specifying a role and an assigned audio channel in the recording. Leave empty when shouldDiarize: true

Response

201
application/json
Returns the generated transcript, including participant roles and timestamps for each utterance.
​
id
string

The unique identifier of the transcript.

​
metadata
object

Additional information about the participants involved in the transcript.

​
transcripts
object[]

An array of transcripts.

Was this page helpful?