Interview Transcription with Every Speaker Labelled
Upload the interview and the transcript comes back split by speaker, with a timestamp on every answer; rename “Speaker 1” to the person’s name once and it changes everywhere.
Phone, Zoom, recorder or camera audio · 120+ languages · files up to 8 GB
Rename a speaker once, it changes everywhere
What made you leave the agency?
I wanted to build one product, not forty pitches.
Did you plan the first hire?
Not at all. She found us.
Click or drag & drop to upload your audio or videoTap to upload your audio or video
MP3, MP4, M4A, MOV, MKV, WEBM, AVI, WAV, FLAC, AAC, OGG, OPUS, WMA, WMV
No credit card required · Stored in the EU · Never used for AI training
What an Interview Transcript Is Used For
Find the line, check it against the audio with one click and copy it with its timestamp, so an editor can verify it.
Several interviewers read the same answers instead of relying on one person’s notes, and can share the parts that matter.
A long conversation becomes text you can search, edit into an article or keep in an archive next to the recording.
What an Interview Transcript Looks Like
This is the structure of an exported transcript in DOCX or TXT. Every element can be switched on or off when you export.
- Speaker
- A name on each answer, or only when the speaker changes
- Time
- (12:40 - 12:46) in DOCX and PDF, [00:12:40.000] in TXT
- Text
- Punctuated sentences, grouped into paragraphs every 5–30 seconds if you prefer
- One person only
- Filter the editor to the interviewee and export just their answers
- File types
- DOCX, PDF, TXT, CSV or XLSX for reading; SRT or VTT if the interview is a video
- Second language
- Add a translation of the whole interview, with the same speakers and times
Before You Record or Upload
Most fixes in an interview transcript come from the recording, not the software.
Distance
Keep the phone within a metre
A recorder close to both people beats an expensive microphone across the room. On calls, record on your side of the line, not over a speakerphone.
Speakers
Tell it how many voices to expect
When you turn on speaker recognition, choose how many people speak, from 2 to 5. Two-person interviews are labelled most reliably; with more people, check the first minutes and move any line that landed on the wrong voice.
Consent
Ask before you record
Rules on recording conversations differ by country and US state. Get consent on the recording itself; it also helps to have the person say their name early on.
How to Transcribe an Interview
From recording to finished text in three steps.
Add the audio or video file, or paste a link to it on Google Drive, Dropbox or YouTube.
Choose the language, turn on speaker recognition and set how many people speak. Then rename Speaker 1 and Speaker 2 to real names in the editor.
Click a line to hear it, fix names and terms, then export DOCX, PDF or TXT with or without timestamps.