Powered byChatGPTClaudeGoogle Gemini
Works withGoogle DriveDropboxOneDrive
Available onWebExtensionSoonDesktopSoonWindowsSoonAndroidSooniOSSoonMacSoon
Works inChromeFirefoxSafariEdge
Speaker diarization

AI speaker diarization

Automatically detect and label every speaker in your recording. Rename speakers once and the labels apply across the whole transcript and all exports.

Try it now, no signup

Record live or drop in a file (up to 30 MB) and watch it transcribe.

Tap to start recording from your microphone

Speaker diarization answers the question "who said what". RealtimeVoiceKIT separates voices automatically and labels each one, even on overlapping conversations, so multi-person interviews, panels, and calls stay easy to read, quote, and attribute.

Great for

Interviews

Keep questions and answers cleanly attributed to each person.

Panels & meetings

Track every participant across a long, multi-voice conversation.

Legal records

Produce speaker-attributed transcripts for the record.

Podcasts

Label hosts and guests automatically for show notes and clips.

What's included

Automatic speaker detectionEditable speaker namesWorks on overlapping speechCarried into SRT & VTT100+ languages

How it works

Drop audio · video · URLinterview.mp3
01

Upload

Add a multi-speaker audio or video file, or paste a URL.

Speaker 1
02

AI separates voices

Each speaker is detected and labeled automatically as it's transcribed.

ENES · FR · DE
TXTSRTVTT
03

Rename & export

Rename speakers once and export labeled text, SRT, or VTT.

Frequently asked questions

What is speaker diarization?

Speaker diarization is the process of detecting how many people are speaking and labeling which speaker said each segment, the "who said what" of a transcript.

Does it work with overlapping speakers?

Yes. The AI separates and labels voices even when conversations overlap, then you can rename speakers as needed.

Can I edit the speaker labels?

Yes. Rename a speaker once and the label updates across the entire transcript and every export.

Is diarization included for free?

Yes. Speaker labels are included on the Free plan along with 10 transcription minutes every month.

Label every speaker automatically

Get speaker-attributed transcripts free, 10 minutes every month, no credit card.