How do I get speaker labels and names?
- Record, import a file or load a YouTube video as usual.
- Choose the Number of Speakers: Automatic, or a number from 1 to 32. Verbi asks after you tap Stop, after an import and in the YouTube import sheet.
- Open the finished transcript and tap Rename Speakers.
- Type a name for each voice. Leave a field empty to go back to the default label, such as “Speaker 1”.
What should I know about speaker detection?
- It’s part of Verbi Pro on iPhone and Android. Free transcripts don’t have speaker labels.
- Number of Speakers is an upper limit, not a promise: Verbi may find fewer voices. Leave it on Automatic if you’re not sure.
- Names are used in the transcript, the summary, AI Chat and exports.
- Rename Speakers appears only when the transcript has speaker labels.
- Verbi tells voices apart; it doesn’t know who the people are. You give the names.
- People talking over each other is the hardest part to separate. Recordings where one person speaks at a time come out best.
- To keep the labels consistent in a long recording, short clips of up to four voices are sent along with later parts of the audio for transcription.
Frequently asked questions
Can I use speaker detection on the free plan?
No. It’s part of Verbi Pro. See what Pro adds.
What does Number of Speakers do?
It tells Verbi the most voices to expect in this recording. Verbi may detect fewer. Choose Automatic if you don’t know.
Where do the names show up?
In the transcript, the summary, AI Chat and exports such as TXT and PDF.