Skip to main content

Speaker Identity Tagging: Submit Audio Samples

Trish Griffin avatar
Written by Trish Griffin
Updated over a month ago

What is this?

This article provides an overview of the process for providing audio samples for your agency personnel.

Note: You will need to set aside about 10-15 mins to complete each user. The actual recording samples take the users 7-10 mins to complete.

Why am I learning it?

Providing audio samples allows the CommsCoach AI system to recognize and correctly label the call taker's voice in transcripts.

What will I learn?

By the end of this module, you will be able to...

  • Navigate to the Add Audio Samples operation

  • Record your voice for the AI system

  • Save your work

How to Submit Audio Samples for Speaker Identity Tagging

Navigate as follows: Home > Settings > Speaker Identity > Add Audio Samples

Click the blue Add Audio Samples button for the appropriate user.

Respond to the Dialog Box regarding Microphone access

A new side window will pop up with the user name at the top and 3 phrases listed.

  • Each Phrase should have a blue start button.

Select a Phrase Group and click Start

You are going to read the words from the blue box into your microphone

Click the Start Recording button to begin recording

Click Stop Recording when you are done, or need to restart.

To Retry, select the Retry Button

To Record again, click Start Recording

To listen to the recording, click the Play Button

To Save Audio and move on to the Next Step, click the Blue Button

The first sample has been recorded.

The second sample is ready to be recorded.

Click Start Recording to proceed.

Repeat steps until all Phrases have been recorded.

X out of Phrase 1 Recording Dialog Box

Note Phrase 1 Completion Progress.

Begin Phrase 2 by clicking Start Button

Proceed through Phrase Groups 2 and 3 until finished.

Did this answer your question?