-
What is Post-call Transcription?
Post-Call Transcriptions offer a session transcription generated by Vonage AI from an individual session Archive. -
How can I enable Post-call Transcription?
When sending the individual archive request, you can include "hasTranscription=true" to enable transcription for that session.
Example:
{
"sessionId": "1_MX40NzY0MDA1MX5-MTcyMTI5NjU4OTY2Nn5MNlVIWE5SLzN0WGJOVjNRSFQ1QlFYZTN-fn4",
"hasAudio": true,
"hasVideo": true,
"hasTranscription": true,
"name": "archive_test",
"outputMode": "individual"
}
-
Does Post-call Transcription work with both Individual and Composed Archive Mode?
Post-call Transcription works only with individual archives. -
Does Post-call Transcription work with Tokbox?
Yes, Post-call Transcription is available for both Tokbox and Unified. However, Tokbox account customers must submit a support request to enable this feature, which is in line with our fair usage policy. For high-volume usage, transitioning to the Unified platform is recommended. -
What are the languages supported by Post-call Transcription?
Only English transcriptions are currently supported. -
Can I use Post-call Transcription with Vonage Video Express?
No, Post-call Transcription is not available with Vonage Video Express. -
How many streams can be analyzed from a single session?
Up to 50 streams with a maximum of 120 transcribed minutes. -
How does Post-call Transcription pricing work?
For Unified Environment: Transcription is charged at $0.04500/€0.04100 per minute -
If the transcription upload to the customer-configured S3 bucket fails, does the retry or fallback mechanism work similarly to the archive upload?
Yes, the retry mechanism for PCT operates exactly the same as for regular archive uploads. -
In cases where the transcription falls back and is uploaded to the Vonage cloud, will the customer need to use an HTTP GET request to obtain the download link for the transcription?
When the transcription status changes, the customer should receive a callback that includes the download URL. If no callback is registered, the download link can only be retrieved through an HTTP GET request. -
Even though multiple users are joined in the session, the transcription file is a single JSON file. How do we differentiate between the users?
Each transcription entry in the file is associated with a specific channel number assigned to each stream.
The file also includes channels_metadata, which provides stream ID information to each channel.
Additional Information:
For additional information, please refer to our developer documentation.