POST
/
interactions
/
{id}
/
transcripts
/
cURL
curl --request POST \
  --url https://api.{environment}.corti.app/v2/interactions/{id}/transcripts/ \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --header 'Tenant-Name: <tenant-name>' \
  --data '{
  "recordingId": "f47ac10b-58cc-4372-a567-0e02b2c3d479",
  "primaryLanguage": "en",
  "isDictation": true,
  "isMultichannel": true,
  "diarize": true,
  "participants": [
    {
      "channel": 123,
      "role": "doctor"
    }
  ],
  "modelName": "base"
}'
{
  "id": "f47ac10b-58cc-4372-a567-0e02b2c3d479",
  "metadata": {
    "participantsRoles": [
      {
        "channel": 123,
        "role": "doctor"
      }
    ]
  },
  "transcripts": [
    {
      "channel": 123,
      "participant": 123,
      "speakerId": 123,
      "text": "<string>",
      "start": 123,
      "end": 123
    }
  ],
  "usageInfo": {
    "creditsConsumed": 123
  }
}

Authorizations

Authorization
string
header
required

Input your token

Headers

Tenant-Name
string
required

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

Example:

"copiloteu"

Path Parameters

id
string<uuid>
required

The unique identifier of the interaction. Must be a valid UUID.

Example:

"f47ac10b-58cc-4372-a567-0e02b2c3d479"

Body

application/json
recordingId
string<uuid>
required

The unique identifier for the recording.

Example:

"f47ac10b-58cc-4372-a567-0e02b2c3d479"

primaryLanguage
string
required

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

Example:

"en"

modelName
enum<string>
required

The model name for transcription. By default, only the highest tier is accessible. Check https://docs.corti.ai/about/languages for more.

Available options:
base,
enhanced,
premier
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

Returns the generated transcript, including participant roles and timestamps for each utterance.

id
string<uuid>
required

The unique identifier of the transcript.

Example:

"f47ac10b-58cc-4372-a567-0e02b2c3d479"

metadata
object
required

Additional information about the participants involved in the transcript.

transcripts
object[]
required

An array of transcripts.

usageInfo
object
required