On the AWS Management Console, search for the Amazon Transcribe service and click the name. You will most likely land on the splash screen, as illustrated below, unless you have created transcription jobs before in the target region. On the splash screen, click the Launch real-time transcription button.
If you don’t see the splash screen, you will see an overview of your existing transcription jobs and find a Create job button in the upper right corner of the screen. Click that button to continue.
Next you land in the Create transcription job form.
Give your transcription job a meaningful name in the Name field.
In the S3 input URL field, paste the S3 object URL of your sample recording that you took a note of before. If you have used Amazon Connect to produce a sample call recording, it’s going to be a wav file, so in the Format drop down list, select
wav accordingly. In case you have used Amazon Polly, it’s probably an mp3 file (unless you selected a different format), so select
mp3 in that case.
Amazon Connect uses the right stereo channel for the agent recording and the left stereo channel for the customer recording. Therefore, in the radio button Channel identification, select the
Enabled value. The output will contain a transcription of each channel and a combined transcription of all the channels. In case you have used Amazon Polly, don’t enable it.
Leave the rest untouched and click the Create button to create and launch the transcription job.
You will get back to the overview of your transcription jobs and see that your new job is in status In progress.