Speaker identification

Speaker identification that works across every file in your project

A unique voice fingerprint is extracted from each interview and matched across the whole project. Rename a speaker once and the new label propagates everywhere they appear. Watch the demo below colour two speakers in real time as a clip plays.

Try it now

A working sandbox. No sign-up, no project. Sample data only.

  • Voice fingerprinting runs on our servers. No raw audio is sent to a third-party service.
  • Cross-file matching: name a speaker on Day 04 and Day 17 picks up the label too.
  • Merge or split identities project-wide. Renames apply everywhere instantly.
  • Manual override on any turn re-runs the match and reconsiders nearby appearances.
VOICE-PRINT MATCHING
demo
IN
INTERVIEWER

Tell me about the night the override failed.

How it works

Three steps from raw material to result.

STEP 01
Speaker turn
00:04:31 to 00:04:48 · 17s
Voice fingerprint created
Analysed on server · not shared
Voice fingerprints captured

Each speaker turn is analysed locally on our server to create a unique voice fingerprint. No audio is sent to a third-party speaker service.

STEP 02
Cross-file matches
MATCHDay 04 · Marin Interview
MATCHDay 09 · Marin Followup
REVIEWDay 17 · Ensemble
Matched across the project

Fingerprints are compared against existing project identities. Strong matches auto-group; ambiguous ones surface for review.

STEP 03
Rename once
EM
14 files updated instantly
Including files from 3 weeks ago
One name everywhere

Rename a speaker on any file and the change ripples to every appearance, including files you uploaded weeks ago.

Frequently asked questions

How does cross-file matching work?

Each speaker turn is analysed to create a unique voice fingerprint, then compared against the identities already in the project. Matches above a tuned confidence threshold are grouped automatically; ambiguous ones are flagged for manual review.

Can I merge two speakers I named separately?

Yes. Merge from the speaker panel and all appearances of the absorbed identity are renamed across every file. Splitting one identity into two is also supported.

What if the system gets a speaker wrong?

Correct the label on any turn and the system re-analyses and reconsiders nearby matches automatically. A project-wide cleanup pass can be triggered manually after large edits.

Does it work for two speakers who sound alike?

Voice fingerprinting separates most adult voices reliably even when timbre is close. Identical-twin-level similarity occasionally needs manual review, especially in short turns under two seconds.

Is speaker identification run locally?

No. It runs on our servers, not in your browser. No raw audio is sent to a third-party speaker service.

Related capabilities

Further reading

Background guides and comparisons.

Put speaker identification to work on your project.

Start free with 5 minutes of AI transcription a month. Or book a personalised walkthrough with the team.