Every voice, word for word.
Transcribe audio to text — every voice, word for word
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.
Upload an interview, a lecture or a meeting. In about two minutes you read the first two minutes, with every speaker labeled. If you like it, pay once for this file and get the whole transcript, verbatim and edited.
- 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”.
What you get for $8.90
One payment covers the whole file, up to 3 hours:
- The verbatim transcript: every word as spoken, with the speaker and a timestamp for each paragraph.
- The edited transcript: recognition errors corrected, fillers removed, headings, a short summary and key points, and a list of every change we made.
- Both as Word, TXT and Markdown: 6 files, plus all of them in one ZIP.
- Names instead of "Speaker 1": we suggest names where the recording makes them clear, and you confirm them before you download.
Made for recordings with several voices
Most transcripts go wrong where people take turns: one voice gets split in two, or two voices get merged. Dettalo labels each speaker across the whole file in one pass, so the same person keeps the same label from the first minute to the last, for up to 32 speakers. Tell us roughly how many people speak and type the names you expect: both make the result more reliable.
Pay for the file, not for the month
Subscription apps make sense if you transcribe every week. If you have one interview, one lecture or one meeting, a monthly plan is money you don't need to spend. With Dettalo you read the first two minutes of your own recording for free, pay once if you like it, and get a full refund within 7 days if the result disappoints you.
Files we take
Audio and video up to 3 hours or 2 GB: MP3, M4A (iPhone Voice Memos), WAV, AAC, OGG and OPUS (WhatsApp and Telegram voice notes), FLAC, MP4, MOV, WEBM and more. For videos we transcribe the sound track. A one-hour recording is usually ready in about 10 minutes, and we email you when it is.
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
How accurate is the transcription?
We use ElevenLabs Scribe v2. In the Open ASR Leaderboard's multilingual test it had the lowest word error rate in Spanish, Italian, French and German (2.3–3.3% on read speech), and 2.2% on Artificial Analysis's mostly English benchmark. Noisy rooms and people talking over each other cause more errors, so read the free preview of your own file before you pay. Details on the accuracy page.
What does it cost?
$8.90 per file, up to 3 hours, whatever the length. One payment, no subscription, no account. The price shown on the order button is the one you pay.
What is the difference between the verbatim and the edited version?
The verbatim version is every word the speech recognition heard, fillers and false starts included, with timestamps. The edited version corrects clear recognition errors, removes fillers, splits the text into paragraphs with headings and adds a summary. Nothing is added to what was said, and every change is listed at the end.
Which languages can you transcribe?
More than 90. The language is detected automatically and shown in the preview; if it's wrong, pick the right one and the preview runs again. Accuracy is highest in English, Spanish, French, Italian, German, Dutch, Portuguese and Japanese.
How do I get back to my transcript later?
There is no account. After you pay, we email you a private link. It works for 60 days. If you lose it, enter your email on the My transcripts page and we send it again.
What happens to my file?
If you don't order, the upload is deleted after 24 hours. After an order, the audio is deleted after 7 days and the transcripts after 60 days, or at once if you ask for a refund.