Every voice, word for word.
Interview transcription with every speaker labeled
One file, one price. No subscription.
- No account
- First 2 minutes free
- Private: deleted after 24 hours unless you order
Payment canceled. Your preview is still here.
Free preview: the first 2 minutes
·
Your full transcript
$8.90One file, one price. No subscription.
- Verbatim and edited version
- 6 files: Word, TXT and Markdown
- Every speaker labeled, names you confirm
- Summary and key points
- Money back within 7 days, no questions
Secure payment by Stripe: card, Apple Pay, Google Pay
Cards are only charged once your transcript has passed our check.
Sent. The link works for 24 hours.
For thesis interviews, qualitative research, journalism and podcasts. Upload the recording, read the first two minutes with interviewer and interviewee labeled, then pay once for the whole interview.
- Verbatim + edited version
- 6 files: Word, TXT, Markdown
- 90+ languages
- Every speaker labeled
- Money back within 7 days
Two versions of every transcript
Verbatim Every word as spoken, fillers included.
So, um, how did you, how did you start the bakery?
Well, I I started in 2019 with, uh, one oven and my friend Marco Bell Lucci. The first year was really hard.
Edited Corrected, laid out, with headings and a summary. Nothing added.
How it started
So, how did you start the bakery?
Well, I started in 2019 with one oven and my friend Marco Bellucci. The first year was really hard.
The names you type in fix the spelling: “Marco Bell Lucci” becomes “Marco Bellucci”.
Who it is for
- Students and researchers with thesis interviews or qualitative research: the verbatim version keeps every word, fillers and false starts included, for coding; the edited version reads better in quotes.
- Journalists: every paragraph has a timestamp, so you can go back to the exact moment in the recording and check a quote before it runs.
- Podcasters: the edited version has headings, a short summary and key points, a start for show notes. Panels with several guests work too, up to 32 speakers.
What the transcript looks like
The verbatim version gives every paragraph a speaker and a timestamp. A short example:
Interviewer · 00:14:32
So, um, how did you, how did you find your first clients?Maya Chen · 00:14:37
Mostly friends of friends. The first, uh, the first year I said yes to everything.Interviewer · 00:14:45
Everything?Maya Chen · 00:14:46
Pretty much. Logos, menus, once even a wedding invitation.
The edited version drops the "um" and the repeated words, corrects clear recognition errors and lists every change at the end. Nothing is added to what was said. Speaker names are suggested where the recording makes them clear, for example when people introduce themselves, and you confirm or change them before you download.
Tips for recording interviews
- Pick a quiet room and put the recorder between you, a little closer to the interviewee.
- For remote interviews, use the call's own recording function instead of a phone next to a speaker.
- Let each other finish. Where people talk over each other, the error rate goes up.
- Ask for consent on the recording and have everyone say their name. Names said aloud help us suggest the right speaker labels.
Add a names and terms list
Before the transcription starts, type up to 60 names and terms to get them spelled right: the interviewee's name, organizations, places, products, technical words. In research, your speaker labels can be pseudonyms such as P07; names mentioned during the interview stay in the text, so replace those yourself.
Not sure the quality will hold for your recording? Read the first 2 minutes free, and see the accuracy page for what affects the error rate.
How it works
Upload
Drop an audio or video file, up to 3 hours. No account needed.
Read the free preview
In about 2 minutes you read the first 2 minutes, speakers labeled, verbatim and edited.
Pay once
Enter your email and pay for this file only. No subscription.
Download
We email you a private link. Confirm the speaker names and download 6 files.
What a transcript costs
| Price | How you pay | |
|---|---|---|
| Human transcription (Rev) | $1.99 per minute: about $119 for one hour | Per minute of audio |
| Subscription apps (TurboScribe, Otter) | $16.99–20 a month, or $8.33–10 a month billed yearly | Monthly or yearly plan |
| Dettalo | $8.90 per file, up to 3 hours | Once per file, no subscription |
Questions and answers
Is the verbatim transcript good enough for qualitative research?
It keeps every word as recognized, including fillers, false starts and repetitions, with a speaker and a timestamp for each paragraph: a workable base for coding. Speech recognition still makes mistakes, especially with crosstalk and noise, so check it against the audio before you code or quote.
Can I pseudonymize the people I interviewed?
Yes, for the speaker labels: before downloading you confirm the speaker names, and you can type any label, such as Interviewer and P07. Names mentioned during the conversation stay in the text, so replace those yourself.
Can it handle a focus group?
Up to 32 speakers are labeled across the whole file in one pass. Tell us how many people speak. Expect more errors where people talk at the same time.
Can I quote directly from the edited version?
It reads better for quotes: fillers removed, clear recognition errors corrected, and every change listed at the end. Before you publish, check each quote against the audio, especially names and numbers.
What does a long interview cost?
$8.90 per file of up to 3 hours, whatever the length: a 20-minute and a 2-hour interview cost the same. If your recording is longer than 3 hours, split it into parts.
Who processes my interview recordings?
Speech recognition runs at ElevenLabs (AssemblyAI if it is unavailable), and Claude (Anthropic) writes the edited version. Uploads you don't order are deleted after 24 hours; after an order, the audio is deleted after 7 days and the transcripts after 60 days. Details in the Privacy Policy.