Title: Speaker diarization: who said what in a call | Spellit
Description: Speaker diarization splits a transcript by speaker. Why labels matter for sales calls and how Spellit Notes turns them into names with role and company.
Page: https://spellit.ai/blog/glossary/speaker-diarization/

---

[Blog](https://spellit.ai/blog/) [Glossary](https://spellit.ai/blog/glossary/)

# Speaker diarization: who said what in a call

Speaker diarization is the step in transcription that divides a recording by speaker, so that each line is attributed to a person rather than to an undivided stream of words.

Oleg Kulakov CEO, Spellit 3 November 2026 1 min read

Without it, a transcript is a block of text. With it, you can see that the buyer asked about the contract and the rep answered about delivery. Many things a team wants from a call depend on it: the buyer's exact words on price, the rep's talk time, who promised what.

The common failure is mislabeling. Speakers get swapped, two people are merged, or labels read "Speaker 1" and "Speaker 2" with no link to real names. In a call with several participants, a promise attributed to the wrong person can start a real dispute afterward.

Before you quote anyone from a transcript, check the label against the recording at that timestamp. It takes seconds, and a wrong attribution can cost more than the time.

Labels are most useful when they carry meaning: a name, a role and a company. "Dana, procurement, the buyer's company" tells you whose view you are reading, which "Speaker 2" never does.

Spellit Notes cleans up the transcript so that speaker labels become real names with role and company, while the speech itself stays word for word. The same names then feed the summary and the tasks, so an owner or a commitment points at an actual person in your organization.

See [Spellit Notes](https://spellit.ai/products/notes/) for the full flow from recording to summary.

Related terms: [call transcription](https://spellit.ai/blog/glossary/call-transcription/), [talk ratio](https://spellit.ai/blog/glossary/talk-ratio/) and [parking lot](https://spellit.ai/blog/glossary/parking-lot/).

Keep reading: [How accurate are AI meeting notes, really](https://spellit.ai/blog/playbooks/how-accurate-are-ai-meeting-notes/).

See the demo now. Then run it on yours.

A live demo of our products and a real conversation about the growth problem you need to solve.

[Book a demo](https://spellit.ai/request-demo/)

See it on your own calls

A live demo and a real conversation about your growth problem.

[Book a demo](https://spellit.ai/request-demo/)

45 minutes · nothing to prepare

## More in Glossary

[All Glossary](https://spellit.ai/blog/glossary/)

- [Glossary Timing objection: when the buyer says not now A timing objection is a buyer's statement that the moment is wrong, as in "not this quarter", "after the holidays" or "come back in spring".… 3 November 2026 1 min read](https://spellit.ai/blog/glossary/timing-objection/)
- [Glossary Talk ratio: reading the split on a sales call Talk ratio is the share of a conversation's speaking time taken by one side, most often the salesperson.… 3 November 2026 1 min read](https://spellit.ai/blog/glossary/talk-ratio/)
- [Glossary Spaced repetition: keeping answers fresh Spaced repetition is a learning method that brings material back at increasing intervals, so it is recalled at the moment it would otherwise fade.… 3 November 2026 1 min read](https://spellit.ai/blog/glossary/spaced-repetition/)
- [Glossary Skills gap analysis: ranking what a rep misses A skills gap analysis compares what a rep actually does on calls with a defined standard, then lists the differences in order of importance.… 3 November 2026 1 min read](https://spellit.ai/blog/glossary/skills-gap-analysis/)
