Speaker labels · free up to 30 minutes
Interview Transcription
Upload an interview recording and get an interview transcript that reads like a script: each turn labeled with its speaker, each sentence with its time. An interview up to 30 minutes long is transcribed in full for free.
Transcribe files
Drop audio or video files here
MP3, M4A, WAV, FLAC, OGG, MP4, MOV and more · up to 3 files at once
Browse filesNo account needed: 3 files a day free, full transcripts up to 30 min each. for 30 more free minutes.
- Each speaker labeled
- Timestamp on every sentence
- Word export for quotes
- Free up to 30 min per interview
How to transcribe an interview
- 1
Upload the recording
Any audio or video file works: a phone recording, a Zoom or Teams file, or a recorder’s MP3 or WAV.
- 2
Set the number of speakers
Open the settings and choose 2 for a one-on-one interview, or the exact number for a panel. This gives the cleanest speaker labels.
- 3
Pull your quotes
Read the transcript on the page, use the timestamps to check a quote against the audio, and download Word or TXT for your notes.
Free limits at a glance
| Without an account | Free account | |
|---|---|---|
| Free files per day | 3 | 3 |
| Files up to 30 minutes | Full transcript | Full transcript |
| Files over 30 minutes | First 10 minutes | First 10 minutes, or use your minutes |
| Extra minutes | None | 30 on sign-up |
| File size | 500 MB | 2 GB |
| Files at once | 3 | 50 |
| TXT, Word, SRT and VTT downloads | After a free sign-up | Yes |
| Credit card | No | No |
Every file: up to 10 hours, 90+ languages, speaker labels and timestamps. After that, one-time packs: 3 hours for $6.99, 15 hours for $19.99 or 50 hours for $49.99, and minutes never expire. The original audio is deleted after transcription (within 48 hours at most), and we never use your files to train AI models.
Who said what, and when
Speaker labels are on by default. Each turn is marked Speaker A, Speaker B and so on, in the order people first speak, so in most interviews Speaker A is the interviewer. Every sentence starts with its timestamp, which is what you need to find a quote again or cite it precisely.
Labels are most reliable when you set the number of speakers and people do not talk over each other. Short interjections like "right" or "mm-hm" in the middle of someone else’s answer can occasionally be given to the wrong speaker, so check the lines you plan to quote.
Interview transcription for journalists, researchers and hiring teams
Journalists use the timestamps to verify quotes before publishing. Researchers download Word files to code interviews in their analysis software; most qualitative tools import DOCX. Hiring teams keep a written record of candidate interviews to compare answers side by side.
- Clean, readable text: filler sounds like "um" and "uh" are left out
- Exports: Word (DOCX), TXT, and SRT or VTT if the interview is a video
- Batch upload: up to 50 interviews at once with an account
- 90+ languages, detected automatically
What an interview costs
Most interviews are free or cost very little. Up to 30 minutes is free in full, 3 interviews a day. Longer ones use minutes from a one-time pack, charged for the real length rounded up to the next minute.
| Interview length | What you pay |
|---|---|
| Up to 30 minutes | Free (3 a day) |
| 45 minutes | 45 minutes from a pack (about $1.75 with the 3-hour pack) |
| 1 hour | 60 minutes (about $2.33, or $1 with the 50-hour pack) |
| A study of 20 one-hour interviews | 1,200 minutes, covered by the 50-hour pack for $49.99 |
How to record an interview that transcribes well
Put the phone or recorder between you and the other person, not in front of you. Do a ten-second test and listen back. For remote interviews, record the call itself (Zoom, Teams, Meet) rather than the speakerphone in the room. Always ask the interviewee for consent before you record.
Frequently asked questions
Can it tell the interviewer and interviewee apart?
Yes. Each speaker gets their own label (Speaker A, Speaker B). Setting the number of speakers to 2 in the settings gives the most reliable labels for a one-on-one interview.
Can I rename Speaker A and Speaker B?
Not on the page yet. Download the Word file and use find and replace to swap the labels for names in a few seconds.
Is it a verbatim transcript?
It is a clean transcript: every word is written out, with punctuation added and filler sounds like "um" and "uh" left out. If your research needs strict verbatim with pauses and false starts, edit the transcript or use a human service.
Is interview transcription free?
Interviews up to 30 minutes are free in full, 3 a day, without an account. Longer interviews show their first 10 minutes free, and signing up adds 30 free minutes.
Is it safe for confidential interviews?
Files are stored privately and only used to make your transcript. The original audio is deleted after transcription, within 48 hours at most, and we never use your files to train AI models. Transcripts stay in your account until you ask us to delete them.
Which languages can an interview be in?
More than 90, including English, Spanish, French, German, Portuguese, Japanese and Chinese. The language is detected automatically, or you can pick it.
How much does it cost to transcribe a one-hour interview?
A one-hour interview uses 60 minutes from a pack: about $2.33 with the 3-hour pack, or $1 with the 50-hour pack. An interview up to 30 minutes is free.
How long does interview transcription take?
A one-hour interview is usually ready in a few minutes. You can close the page; with an account we email you when it is done.
Can I find a quote by its timestamp?
Yes. Every sentence in the interview transcript starts with its time in the recording, so you can jump to that point in your audio player and check the quote before you use it.
More ways to transcribe
Try it on your own file
Files up to 30 minutes get a full transcript free, no account needed.
Upload a fileUpdated October 2026