Skip to main content

Generate transcript

This endpoint enables you to generate a transcript of a recording. The transcript will contain the spoken content, the duration of each spoken content, the speaker, the start and end time of the spoken content, and the sentiment analysis.

It may take up to 20 minutes to generate the transcript. Once generated it will be displayed under the get recordings with transcript endpoint.

Before we start

You are only able to get the transcript of a recording of a meeting. To record a meeting, you must enable the recording feature during the meeting. It can be achieved by either clicking the toolbar button 'Record' at the interface or by invoking the toogleRecording() method on the Video Conference.

How to use

You can use the following cURL to obtain a response on the endpoint:

curl --location --request POST https://api.superviz.com/recordings/transcripts \
--header 'Content-Type: application/json' \
--header "client_id: ${YOUR CLIENT_ID}" \
--header "secret: ${YOUR SECRET}" \
--body '{
"recordingId": "RECORDING_ID",
"language": "en-US"
}'

HTTP Request

POST https://api.superviz.com/recordings/transcripts
NameDescription
recordingIdThis field contains the unique identification of the recording, which can be found with the GET Recordings endpoint.

Headers

When using this endpoint, you need to provide the Authorization Bearer token and the passphrase. The following headers are required:

NameDescription
client_idRequired. You need to use the Client ID to authenticate in this repository. You can retrieve your Client ID under the Dashboard > Developer > Keys.
secretRequired. You need to use the Secret Key to authenticate in this repository. You can create a new API Secret under our Dashboard > Developer > Keys.

Request body

The request body must contain the following fields:

NameTypeDescription
recordingIdstringThis field contains the unique identification of the recording, which can be found with the GET Recordings endpoint.
languagestringThis field contains the language of the spoken content. For now, we only support en-US.

Example:

{
"recordingId": "RECORDING_ID",
"language": "en-US"
}

Response

Status code 200 will indicate that the request was successful. It will take up to 20 minutes for the transcript to be generated. Once generated it will be displayed under the get recordings with transcript endpoint.