Pepys
9,438,517minutes transcribed

Film and documentary transcription, built for the edit

Drop your interviews, dailies, and verite footage – get a speaker-labeled transcript plus the themes, the standout quotes, and a Q&A breakdown, ready to paper-edit before you open the timeline.

or paste a link
InstagramTikTokYouTubeFacebookSpotifyApple Podcasts

60 min free · no card required · we never train on your audio

PodcasterJournalistContent creatorResearcherStudent
Trusted by 100,000+ creators, podcasters, journalists & researchers

How do you transcribe interviews?

To transcribe film and documentary footage, upload your interviews or dailies, or paste a link, and Pepys returns a speaker-labeled transcript in minutes, plus the standout quotes, recurring themes, and a clean Q&A breakdown for your paper edit. It's pay-as-you-go with no subscription, and credits never expire.

Upload or paste a link

Drop your interview or paste its link – any audio or video, in any language.

Get your transcript

A clean, speaker-labeled transcript with AI notes tuned to your format, ready in minutes.

Edit and export

Fix anything inline, then export to SRT, VTT, TXT, DOCX, PDF, or JSON.

Made for filmmakers

  • Reliving the tape to find one line

    Every interview is an hour you sit through again to find the answer that carries the scene – Pepys turns the footage you shot into text you can read and search.

  • A line that hides in the waveform

    A great moment jumps off a page where it disappears in a scrub bar – search a half-remembered phrase across the whole shoot and jump to the timecode.

  • Sending an unreleased cut to a stranger

    Handing dailies of a protected subject to a contractor is a risk you can't take back – Pepys never trains on your footage, and you pay per project with credits that never expire.

Built in, not bolted on

The story beats, the strongest soundbites, and a recap for the edit

Every interviewis analyzed automatically the moment it’s transcribed. Here’s a real sample, run through it.

walter-kitchen-day09.movAI analysis, built in
AI analysis

The Sentence That Became the Spine: A Director on the Interview That Reshaped Her Film

A documentary director walks through the on-camera interview she nearly cut for time – a retired miner named Walter, booked as a ninety-second supporting voice. When he spoke about the day the pit closed, one line reorganized the entire film around it. She explains why she refused to ask him to repeat the moment, why she held eleven seconds of silence instead of cutting away, and how reading forty hours of footage as transcript, not waveform, is where the edit actually gets built. Her throughline: the footage is never the film; structure is the real edit.

Themes

The interview that quietly outgrows its place in the cutWhy repeating a moment turns truth into performanceHolding silence over cutting to safe B-rollReading footage as transcript before touching the timelineStructure, not coverage, is where the film is made

Notable quotes

  • The town didn't die when the mine closed, it died the day we stopped talking about it.
  • The moment you ask someone to repeat their grief, it becomes a performance of grief.
  • A face holding back is more cinematic than any B-roll I could shoot.
  • The edit isn't built in the edit suite anymore. It's built in the margins of a transcript.
  • The footage is never the film. The film is the order you put it in.

Q&A

What was the line that made you realize this wasn't a supporting character anymore?

It was Walter's line, quoted exactly: 'The town didn't die when the mine closed, it died the day we stopped talking about it.' The director and her focus puller both recognized it as the spine of the movie, and the rest of the film reorganized itself around that sentence.

A lot of directors would chase that line and ask for a cleaner take. Did you?

No. She calls resisting that urge the hardest discipline in documentary, because asking someone to repeat their grief turns it into a performance of grief that you can hear in the cutting room. Instead she let the silence run for eleven seconds and said nothing.

How did you know to hold eleven seconds of silence instead of cutting away?

She learned it the expensive way on her first film, where she covered every silence with a hand, a window, or a photograph and audiences felt managed. Now she trusts the face, because a face holding back is more cinematic than any B-roll she could shoot.

You shot roughly forty hours of interviews for a ninety-minute film. How do you find moments like Walter's in that haystack?

Transcripts. She reads the full forty hours as text and highlights on paper before touching the timeline, because a great line jumps off a page where it can hide in a waveform. As she puts it, the edit is built in the margins of a transcript, and structure, not coverage, is the real edit.

Clean, speaker-labeled, click-to-seek

0:00 / 2:38

Ask, don’t scrub

Ask the transcript anything.

An hour-long recording? Don’t skim it – ask. Every answer stays grounded in your transcript and cites the exact timestamp, so you can jump to the moment and check it yourself.

walter-kitchen-day09.movAsk AI

Which line did she say became the spine of the film?

It was Walter's line, quoted exactly: 'The town didn't die when the mine closed, it died the day we stopped talking about it.' She says she and her focus puller both knew that was the spine of the movie, and everything reorganized itself around that sentence.

Cited0:39

Why didn't she ask him to repeat the moment for a cleaner take?

She calls resisting that the hardest discipline in documentary, because the moment you ask someone to repeat their grief, it becomes a performance of grief you can't un-hear in the cutting room. Instead she let the silence run for eleven seconds and didn't say a word, since she now trusts the face over cutting to B-roll.

Cited1:081:36
Ask anything about this transcript…

Grounded in your transcript – if the answer isn’t in the audio, it says so instead of guessing.

Who said what

Speaker labels that survive cross-talk

Automatic speaker diarization. Two people, four people, cross-talk and interruptions – interviews, panels, messy meetings. Pepys keeps each voice on its own line instead of blurring them into one, so you never rewind to figure out who was talking.

Reporter

So the festival nearly didn't happen this year–

Mara Okonkwo

–it almost didn't. We lost the venue three weeks out.

Reporter

Three weeks? How do you even start to–

Mara Okonkwo

You call everyone you know. The whole town pitched in.

Reporter

And that's how it ended up in the park.

  • Paper-edit your interviews

    A clean, speaker-labeled transcript of every interview so you can read, highlight, and build the cut on paper before you open the timeline.

  • Find the line in the haystack

    Search across forty hours of dailies for a half-remembered phrase and jump straight to the timecode instead of rescrubbing tapes.

  • Standout quotes, surfaced

    The most usable lines and answers pulled out for you, ready to drop into a string-out, a trailer, or a festival cut.

  • Festival-ready captions

    Frame-accurate SRT and VTT exports for your screener, accessibility, and the subtitle spotting your distributor will ask for.

Record in any language – 99+ detected automatically

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.

  • YouTubeYouTube
  • TikTokTikTok
  • InstagramInstagram
  • FacebookFacebook
  • SpotifySpotify
  • Apple PodcastsApple Podcasts
  • or any file

Export to any format

  • TXT
  • Markdown
  • DOCX
  • PDF
  • SRT
  • VTT
  • JSON

Most useful for filmmakers: SRT · VTT · Transcript (DOCX) · TXT · PDF

Timestamps, speaker labels, and subtitle timing carry through to every export.

Why filmmakers pick Pepys

  • No subscription – pay per project, and credits never expire between shoots.

  • Themes and standout quotes are pulled for you, not a separate copy-paste into a chatbot.

  • Upload dailies straight off the card, or paste a link – no wrangling files first.

  • Speaker labels keep your director, interviewer, and subjects from blurring into one block.

What filmmakers say

  • I used to tell myself I would repurpose long videos and then absolutely not do it. Pepys gives me the transcript, chapters, and hook ideas, which means the clips actually happen instead of living forever on my to-do list.
    Daniel K.Daniel K.YouTube creator · Long video to shorts
  • I had hours of interviews and that horrible feeling that the story was somewhere in there, but I could not see it yet. Reading the transcripts made the shape of the film visible. I could search, highlight, pull quotes, and start building the cut before opening the timeline.
    Giulia F.Documentary filmmaker · The edit got unstuck
  • The translation is useful, but the magic is that the timing survives. That is the part that used to ruin my afternoon.
    Lucas D.Lucas D.Subtitle translator · Timing survived translation

Film and documentary transcription – questions, answered

How do I transcribe a documentary interview?

Upload the interview file or paste its link, and Pepys returns a speaker-labeled transcript in minutes, along with the standout quotes, recurring themes, and a clean Q&A breakdown you can paper-edit from.

Can it handle forty hours of dailies without me babysitting it?

Yes. Queue as many files as you have and let them process. Each comes back as its own searchable, speaker-labeled transcript, so you can read across the whole shoot as text rather than scrubbing tapes one at a time.

Does it tell the interviewer and subjects apart?

Yes. Speaker diarization separates each voice, so a director, an interviewer, and a subject come back labeled instead of as one wall of text. You can rename a speaker once and it updates everywhere in the transcript.

Will the captions line up frame-accurately for my screener?

Exports are timestamped, so SRT and VTT drop into your editor or player without manual re-syncing. That covers screeners, accessibility, and the subtitle spotting a distributor asks for.

Can it transcribe interviews in another language and subtitle them?

Yes. It auto-detects the spoken language across 99+ languages, and you can transcribe in the original and export translated subtitles with the timing preserved, so a foreign-language subject doesn't mean a separate round of contractor work.

Do you train on my footage?

No. Your footage is never used to train a model. For unreleased films and protected subjects, that point is non-negotiable, and it's why editors trust it for sensitive material.

Do I have to subscribe?

No. Pepys is pay-as-you-go – buy a block of hours, use them across this film and the next, and the credits never expire between projects. You can start free with 60 minutes, no card.

Start your first interview free

More industries

Popular tools

Don't just take our word for it.

Ask ChatGPT, Claude, or Perplexity whether Pepys is the right fit for filmmakers.

Turn your next interview into a transcript, the standout quotes, and a paper edit – and pay only for that project.

Pay as you go – credits never expire, nothing to cancel. Or start free with 60 minutes, no card.