Interview Diarization
Upload an interview recording or paste a link and get it split by speaker – interviewer and guest, clearly labeled with timestamps.
Accepts an interview recording (MP3, M4A, MP4…) or a link · returns a speaker-labeled, timestamped transcript that separates each voice.
Diarization labels distinct voices per chunk as Speaker 1, Speaker 2, and so on – it separates who is speaking, not who they are by voiceprint identity. Rename the labels to real names after transcription.
60 min free · no card required · we never train on your audio
How do I separate the interviewer and guest in a transcript?
To diarize an interview, upload the recording or paste a link into Pepys and it returns a clean, timestamped transcript split by speaker – Speaker 1, Speaker 2, and so on – so the interviewer and guest are clearly separated, in 99+ languages, in minutes. Your first 60 minutes are free, no card required.
How interview diarization works
Upload audio or paste a link
Drop in your interview recording or paste a link – any format, any length.
Get the speaker split
AI transcribes the interview and labels each turn by speaker with timestamps, ready in minutes.
Edit and export
Rename Speaker 1 to the guest's name, tidy anything inline, then export to TXT, Markdown, DOCX, PDF, SRT, or VTT.
An interview transcript is only useful if you can tell who said what. A wall of unattributed text means re-listening just to figure out where the question ends and the answer begins. Pepys diarizes the recording for you: upload the file or paste a link and it returns the conversation split into speaker turns – interviewer and guest clearly separated, each with timestamps.
From there you can rename the generic labels to real names, pull a clean quote attributed to the right person, and jump to any exchange in seconds. It works across 99+ languages with auto-detection, we never train on your audio, and you pay only for the minutes you transcribe – credits never expire.
Clean paragraphs. No more um's and ah's.
The left is what Pepys hands back – logical paragraphs with the filler stripped out, punctuated and readable. The right is the raw, one-line-per-segment dump most transcribers leave you with.
um so yeah everyone keeps telling you to like lead with your best line right but uh honestly if you give away the whole answer in the first second you know there's basically no reason for anyone to keep watching so the hook isn't kind of the smartest thing you say it's like a loop you open that they need to close and um that's the part that actually keeps people around
RawAutomatically splits the interview into speaker turns – interviewer and guest
Timestamps on every turn so you can jump straight to any exchange
Rename the labels to real names and pull cleanly attributed quotes
99+ languages, auto-detected · we never train on your audio · credits never expire
Works with the platforms you live in.
Paste a link from YouTube, TikTok, Instagram, Facebook, Spotify, or Apple Podcasts – or drop in any audio or video file. We transcribe it once, then you export it however your workflow needs.
- YouTube
- TikTok
- Spotify
- Apple Podcasts
- or any file
Export to any format
- TXT
- Markdown
- DOCX
- SRT
- VTT
- JSON
Timestamps, speaker labels, and subtitle timing carry through to every export.
Interview diarization – questions, answered
How do I separate the interviewer and guest in a transcript?
Upload your interview recording or paste a link on this page. Pepys transcribes it and splits the text by speaker with timestamps – your first 60 minutes are free, no card required.
Does it know the speakers' real names?
No – it labels distinct voices as Speaker 1, Speaker 2, and so on per chunk, not by identity. You rename them to the real names once, and the transcript reads cleanly.
How many speakers can it handle?
It works for a one-on-one interview or a panel – it separates the distinct voices it hears in each chunk and labels each turn so you can follow the conversation.
Can it diarize an interview in another language?
Yes – Pepys auto-detects 99+ languages, and you can translate the finished, speaker-labeled transcript into the language you need.
More free tools
Keep reading
Interview diarization – free to start
Pay as you go – credits never expire, nothing to cancel. Or start free with 60 minutes, no card.