Interview Transcription

1. Drop the recording above: a phone voice memo, a recorder's MP3 or WAV, or the MP4 a video call saved. Files up to 500 MB are accepted.
2. Speaker labels are already on, so the interviewer and the interviewee come back as separate, labelled turns.
3. Press Transcribe. An hour-long interview takes a few minutes, and the job keeps running if you close the tab.
4. Read the summary, then the transcript. Copy it, or download plain text or Markdown free, or a Word file for 3 credits.

The first 10 minutes each day are free, which is enough to check the recording works before paying for the rest. After that it is $0.05 a minute (1 credit). A 45-minute interview is 35 credits once the free minutes are used, $1.75 at the $5-pack rate, and credits never expire.

An interview transcript has one job: let you find and verify a quote fast. That means speaker separation and timestamps, not perfect prose.

Work in this order. Read the summary first to remind yourself what the interview actually contained. Skim the transcript for the passages you want. Then, for every sentence you intend to publish, find its timestamp in your own copy of the recording and listen to it. A quote you have heard back is a quote you can defend.

The DOCX download is built for this: speaker names in bold at the start of each turn, so find-and-replace turns Speaker 1 into your interviewee's name in one pass, and grey timestamps you can strip with a second pass when you are done.

For research interviews that will be coded rather than quoted, export plain text and paste it into your analysis tool — timestamps in square brackets survive the paste and stay searchable.

Put the recorder between you and the interviewee, closer to them than to you. Their words are the ones that matter.

Avoid recording over a video call when you can record locally at both ends; call compression costs you several accuracy points. If you must record the call, record the host side rather than a phone held to a speaker.

Ask the interviewee to say their name and title at the top. You get a clean spelling reference and an easy anchor for renaming the speaker labels.

• One speaker swallows the other. Short interjections like "right" or "mm" from the interviewer can be folded into the interviewee's turn. They rarely matter; check only the turns around a quote.
• Two people talking at once. One voice usually wins and the other is lost. No tool can separate simultaneous speech on a single channel.
• Names and jargon. A company name or a technical term heard for the first time is spelled the way it sounds. Search the transcript for each one and fix it once.
• A remote interview recorded through speakers. A phone held next to a laptop picks up both voices through the room, and the far voice comes out thinner. Record the call itself instead.

Upload an audio or video file and the transcript appears on this page. Every paragraph carries the timestamp it came from, so you can find the moment in the original recording without scrubbing.

Speaker labels are available when the recording has more than one voice: each turn is tagged Speaker 1, Speaker 2 and so on, which is what makes interview and meeting transcripts usable rather than a single undivided block.

Files never become public. The upload is processed, the transcript is attached to your job, and nothing is indexed or shared.

Audio: MP3, M4A, WAV, AAC, FLAC, OGG, Opus, WebM, AMR and WMA.

Video: MP4, MOV, WebM and MKV — the audio track is read and the video itself is ignored, so a 2 GB screen recording transcribes the same as the audio ripped from it.

Files up to 500 MB upload directly from your browser to storage, which means a long recording is not limited by any request size cap. A 90-minute MP3 at a normal bitrate is around 80 MB; an hour of video is usually 300–700 MB.

If your file is larger than 500 MB, export audio only from your editor first. It transcribes identically and uploads in a fraction of the time.

Every format is uploaded as-is; converting first adds nothing, and a careless conversion at the wrong sample rate can hurt.

• WAV is about 10 MB a minute in stereo at 44.1 kHz, so an hour can pass 500 MB. Export it as 16 kHz mono, the rate the models use internally, and it drops to about 2 MB a minute with no loss of accuracy.
• FLAC is lossless at roughly half the size of WAV; an hour of stereo is about 300 MB. Worth keeping as a master you can transcribe again later, though it is barely more accurate than a good MP3.
• MOV from an editor or a ProRes export can run to gigabytes. Export audio only (Command-E in QuickTime) and upload that. A screen recording with no audio track gets a clear error, not an empty transcript.
• WebM from a browser recorder often has a missing or zero duration header. The length is measured from the decoded audio, so timestamps come out right anyway.
• OGG and Opus are what WhatsApp, Telegram and Signal voice notes use. They transcribe well even at low bitrates. Share a WhatsApp note to Files rather than forwarding it, so it is not re-encoded.
• AAC streams without an MP4 wrapper decode directly. If a capture was cut off mid-frame, the last second or two may be missing.
• AMR is narrowband phone audio (300 Hz to 3.4 kHz). Ordinary speech comes through; names, spelled-out addresses and digits are where it slips, so check them against the recording.
• WMA usually means an old dictaphone recording. Expect a few points less accuracy than a modern phone recording, and try one file before paying for an archive. DRM-protected WMA cannot be read by any tool.

Ten minutes of audio a day, across up to three files, cost nothing. You see the transcript, the timestamps, the summary, and you can copy all of it.

When a file is longer than your remaining free minutes, the transcript stops at that point and says exactly where it stopped. Nothing is charged and nothing is hidden behind a signup form — you get a real result for the first ten minutes rather than a blurred teaser.

To transcribe the whole file, add credits. Credits are bought once, never expire, and work across every tool on this site. At $0.05 a minute (1 credit), a 45-minute interview costs $2.25 (45 credits) at the $5-pack rate, or about $1.93 from the $12 pack.

A two-person interview transcribed without speaker separation is nearly useless: you cannot tell a question from an answer without listening again.

With speaker labels on, each change of voice starts a new paragraph tagged with a speaker number. Rename them in your own document afterwards — the DOCX download puts speaker names in bold at the start of each turn precisely so a find-and-replace turns Speaker 1 into a real name in two keystrokes.

Diarisation is not magic. Two people talking over each other, a poor phone line, or someone joining halfway through are all cases where labels drift. Fix the three or four places it matters and leave the rest.

On a clear recording with one or two speakers, expect 92–97% word accuracy. That means roughly one wrong word per two lines, usually a name, a unit, or a technical term.

Things that reliably hurt accuracy: recording from across a room, air conditioning or traffic, several people speaking at once, strong accents in a language the model sees less of, and music underneath speech.

Things that help, and cost you nothing: record at arm's length rather than across a table, use the phone's own voice memo app rather than a video call recording where possible, and say proper nouns clearly the first time they come up.

Before you publish or submit anything, check names, numbers and any sentence you intend to quote. The timestamps make that a minute of work rather than a re-listen.

Upload the video, download the SRT, drop it on the timeline. The cues are split on natural sentence boundaries with millisecond timing, which is what Premiere, Final Cut, Resolve, CapCut and every web player expect.

VTT is the same content in the format HTML5 video wants, with speaker names as voice tags so a player can style each speaker differently.

Subtitle files always need a human pass — line lengths, a mis-heard brand name, a laugh transcribed as a word. Editing an SRT that is 95% right takes a few minutes. Typing one from scratch takes an hour per ten minutes of footage.