Create Transcript

Create a transcript from an audio file uploaded to the interaction via /recordings endpoint.

Each interaction may have more than one audio file and transcript associated with it. Audio files up to 60 min in total duration, or 150 MB in total size, may be used.

By default, requests will process synchronously for 25 seconds before timeout, upon which processing will continue asynchronously. Set the async parameter to true to receive the location header immediately and process the request asynchronously. Read more here.

POST /interactions/{id}/transcripts

cURL

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
    }
  ],
  "async": true
}
'

201

{
  "id": "f47ac10b-58cc-4372-a567-0e02b2c3d479",
  "metadata": {
    "participantsRoles": [
      {
        "channel": 123
      }
    ]
  },
  "transcripts": [
    {
      "channel": 123,
      "participant": 123,
      "speakerId": 123,
      "text": "<string>",
      "start": 123,
      "end": 123
    }
  ],
  "usageInfo": {
    "creditsConsumed": 123
  },
  "recordingId": "f47ac10b-58cc-4372-a567-0e02b2c3d479"
}

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:

"base"

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/stt/languages for more.

Example:

"en"

isDictation · boolean

If true, spoken punctuation will be converted to symbols (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

Show child attributes

async · boolean

If true, the request will return immediately with a 202 status and the transcript will be processed asynchronously. Poll Get Transcript Status to check transcript processing status - processing, completed, failed.

Response

201

application/json

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.

Show child attributes

transcripts · object[] | null · required

An array of transcripts.

Show child attributes

usageInfo · object · required

Credits consumed for this request.

Show child attributes

recordingId · string<uuid> · required

The unique identifier for the associated recording.

Example:

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

status · enum<string> · required

The current status of the transcript processing.

Available options: completed, processing, failed