É«ÇéÍøÕ¾

General

You should consider the following tips in preparation for recording an interview for transcription with Griffith's Speech-to-text service.

1. Please speak as clear as possible. Refrain from speaking too fast.
2. Try not to speak over each other. The transcriptions will not be able to differentiate the speakers and can add it all into the same sentence.
3. Pause between sentences. AI uses gaps between voices for punctuation.
4. When conducting phone interviews, please do not use a separate recorder that is external to the phone, if it is possible use the internal recorder. Using an external recorder for phone interviews will significantly decrease transcription accuracy, especially for the person being interviewed.

Recording Devices

There are several options available to record a phone interview or virtual meeting.

Phone calls using Microsoft Teams

Microsoft Teams Calling has arrived and the Griffith office desk phones are being phased out. (Emergency numbers will work on the desk phone) You can use Microsoft Teams to make calls to phone numbers.  You can review the site for more information on how to use this service.

Recording phone calls works the same way as you record meetings/calls.

Microsoft Teams

A comprehensive video about recording interviews in Teams can be found .

Third Party Audio/Screen recorders

There may be some scenarios where your interview is digital and you can not record using Teams. In these situations you must ensure you have consent and follow the appropriate ethic guidelines but you can use screen recorder or audio recorder software.

On a , use the built in program "Game Bar"

On a use the built in program "Screenshot toolbar"

There are also downloadable tools like and that can be used to capture recording through your computer.

Then you can extract the audio from the video file.  "" is the recommended software, and comes installed on all Griffith computers. Use the following video to help you with the process.

It's recommended to have the following settings when converting the file:

• File type: MP3
• Audio Channels: 1 (to ensure the file works for diarization)

You can also use the command line tool "" to extract audio from video, and to change audio formats.

Diarization is an optional feature within the Speech to Text service that, when enabled, identifies and separates individual speakers in an audio recording. This allows the transcription to distinguish between different voices, making it easier to understand who said what during a conversation or meeting. In the resulting transcript, each speaker is labeled with identifiers such as Speaker 1, Speaker 2, etc., at the beginning of each line, helping to clearly attribute spoken content to the correct individual.

For Diarization to function correctly, the uploaded audio file must be in mono MP3 format. To convert your audio files, we recommend using VLC Media Player. This application may already be installed on your university laptop. If not, you can download it for free from the link provided—.

To convert your audio file using VLC:

1. Open VLC Media Player.
2. Go to Media → Convert/Save.
3. Click Add... and select the audio file(s) you want to convert.
4. Click the Convert/Save button.
5. In the Profile dropdown, select Audio - MP3, then click the spanner (Edit selected profile) icon.
6. In the new window:
   • Go to the Audio codec tab and set Channels to 1.
   • Then go to the Filters tab and enable Stereo to mono downmixer.
7. Click Save.
8. Choose a Destination file path for the converted audio.
9. Click Start to begin the conversion.

Once converted, the mono MP3 file can be uploaded to Griffith’s Speech to Text service, and Diarization will work as expected—labeling each speaker in the transcript as Speaker 1, Speaker 2, and so on.