Skip to main content
Speaker labels often arrive in a shape you did not choose: “Speaker 1” across every file, a moderator named differently in each transcript, or participants who need the session number in their name. The Fix speakers action lets you describe the names and roles you want in your own words and apply them across a selection of files at once. Nothing is written until you review the proposed changes.

Renaming a selection

  1. In the files view, select the files you want to rename speakers in.
  2. Choose Fix speakers in the toolbar.
  3. Describe the naming you want, for example “Prefix each participant with the session number from the file name” or “The moderator is called Sarah in every file”.
  4. Choose Preview changes and wait for the preview.
  5. Review the changes, grouped by file, untick any you do not want, then choose Apply.
File names are part of the context, so instructions can refer to what they encode: a session number, a date, a market, a respondent. The proposal dialog: proposed changes grouped by file, with renames shown as before and after

Reviewing the proposal

Every speaker in the selection is accounted for:
  • Changed rows show the old name struck through and the new name beside it. Role changes are listed too.
  • Unchanged speakers are collapsed behind a count under each file. Expand it to see each speaker with a short reason, for example that the instruction did not say anything about it, or that the name already matches.
An instruction that only resolves some of your speakers still works. The rest are left exactly as they are, and you can go Back to reword the instruction and propose again.

What applying does

Applied changes are confirmed, because reviewing the difference is the check that confirmation asks for. They apply per file, so a speaker who appears in several files is renamed only in the files you selected.
Answers, themes, and other outputs generated before the rename keep the old speaker names until you regenerate them.

Speakers who appear in several files

A speaker merged across files is decided separately for each one, so an instruction that reads file names can give that speaker a different name in each file. Renaming never merges two speakers, and never splits one: each keeps its own turns.

When a name is already taken

If a proposed name is already used by another speaker in the same file, both are kept apart by numbering the later one, Amelia and Amelia (1), the same way confirming speakers does. The same name in two different files is left alone, since those are separate speakers.