Managing speakers in a transcript

When Klang transcribes a recording it automatically detects and labels each speaker. The default labels are generic (“Speaker 1”, “Speaker 2”), so you will usually want to rename them to the actual names. You can also reassign individual segments to a different speaker, add new speakers, or rerun speaker identification with different settings.

How speakers appear in a transcript

Open a transcription from your analysis. At the top of the transcript you will see colored chips for each detected speaker. Below that, each segment shows the speaker name, a timestamp, and the transcribed text.

The colored chips act as quick filters. Click a chip to scroll to that speaker’s first segment.

Rename a speaker

1. In the transcript, click the speaker name next to any segment. The speaker menu opens.

2. Click the edit icon (pencil) next to the speaker you want to rename
3. Type the new name in the text field

4. Click the send icon to confirm

The new name replaces the old one in every segment throughout the transcript.

Reassign a segment to a different speaker

Sometimes Klang assigns a segment to the wrong speaker. To fix this:

1. Click the speaker name on the segment you want to change
2. In the speaker menu, click the name of the correct speaker

The segment updates immediately. A checkmark shows which speaker is currently assigned to the selected segment.

Add a new speaker

If the transcript is missing a speaker, for example when a new person joins partway through a recording:

1. Click any speaker name to open the speaker menu
2. In the Add speaker field at the bottom, type the new speaker’s name
3. Click the send icon

The new speaker is added and assigned to the selected segment.

Rerun speaker identification

If the automatic speaker detection made too many errors, you can rerun it with different settings instead of fixing each segment one by one.

1. In the transcript toolbar, click the Settings icon (gear)

2. Click Rerun speaker identification
3. Choose the number of speakers, or leave it on Automatic
4. Click Run

Klang reprocesses the audio and merges the new speaker assignments into your existing transcript. Any speaker names you renamed before the rerun are preserved where possible.

Note: Rerunning speaker identification replaces the current speaker assignments. If you have made many manual corrections, consider whether a rerun will save time compared to fixing the remaining errors by hand.

Tips for better speaker identification

• Record video meetings with the Klang bot. When Klang joins a Google Meet, Microsoft Teams, or Zoom call, it picks up participant names directly from the meeting. This gives you real speaker names from the start and higher identification accuracy than audio-only uploads.
• Set the number of speakers when uploading if you know how many people are in the recording. This helps the detection algorithm.
• Recordings with clear audio separation between speakers produce better results. External microphones or separate audio channels improve accuracy compared to a single laptop microphone.