Meet the TheyDo Agent

Read more in our blog→

Speaker mapping in interview processing

Overview

When you upload an interview transcript to the Data hub, speaker mapping lets you identify the speakers in the conversation and choose how each one is handled before processing begins. You can mute the speakers you do not want quoted, so the extracted quotes stay focused on customer voices.

PII removal strips personally identifiable information during upload, so you do not need to clean transcripts beforehand.

Note: Speaker mapping is rolling out gradually and may not be available in your workspace yet. If you do not see the speaker mapping step during upload, contact your Customer Success Manager.

Before you start

  • AI must be enabled for your organization, and Remove personally identifiable information must be turned on in Settings > Details & AI. This is an admin action.
  • Your transcript file should be in .txt or .vtt format, or pasted directly as text.
  • Use consistent speaker labels throughout the transcript (for example, Interviewer: and Participant:) so speakers are identified accurately.

Steps

  1. Go to the Data hub.
  2. Select Add source and choose your interview file, or paste the transcript text directly.
  3. Assign the source type Interview to the file. Every file needs a source type before you can submit it for ingestion.
  4. Each text file that needs mapping enters the speaker mapping step on its own, with progress shown as Source N of M. You will see each identified speaker listed.
  5. For each speaker, decide whether to keep them or mute them.
    • Mute researchers, interviewers, or observers you do not want quoted.
    • Leave customers and participants unmuted.
  6. Review your settings, then select Continue to process the file.
  7. TheyDo processes the transcript, removes PII, and makes the quotes available for insight mining and journey enrichment.

Tips

  • Mute the interviewer by default. Unless you specifically need researcher questions included, muting them keeps the focus on customer voices.
  • Check your mapping before you confirm. Speaker mapping cannot be changed after processing. If you need to adjust it, re-upload the file.
  • Batch similar interviews together. Processing interviews from the same segment in sequence makes it easier to stay consistent.