The system allows exporting transcripts in the following ways:
- Running a report
- Exporting
- Using the API
Report
Following the Creating report guide, you can create a Users Speech Transcript Details report containing the transcripts from the filtered conversations.
Export
You can use the Export feature to obtain the media files and the transcripts. The transcript file is a compressed file with VTR extension, containing a plain text file. The text file contains the following fields for each recognized word:
| Field Name | Value | Example |
|---|---|---|
| word | the recognized word | hello |
| confidence | the confidence level | 0.79000000 |
| speaker | participant recognized | speaker1 |
| time | time elapsed in seconds | 189.35000000 |
| duration | length of the word in seconds | 0.50000000 |
API
It is possible to integrate an external application to retrieve a transcription file using the HTTP Business API. The Get Call Information API call can return either a plain text file or the transcription format, depending on the call.
Transcript file format
The VTR file format (with .vtr extensions) contains the transcript text and other information form speech analysis. It is a human-readable JSON formatted text file compressed with Zip. Non-ASCII characters are encoded with UTF8. See detailed specifications of the format here: Verba transcript file (.vtr) format