up to 30 minutes per file on the free plan, no minute limit on Pro
Instagram transcript
The transcript of an Instagram video
Instagram transcript: the words spoken in a video of the feed as text with a timecode on every line, so an interview can be searched. Free $0, 3 files a day.
3 files a day up to 30 minutes, free99+ languagesSpeaker separation and timestamps
In short
Upload the file of a video from the feed and you get the words that were spoken, line by line, with the time of every line. One file is up to 30 minutes, so a long interview is cut into parts. Free $0, 3 files a day.
How to get the transcript of an Instagram video
- 1
Save the file of the video
The service takes a file, not a link: download the video to the phone or the computer, and that file is the whole input. The picture is never analysed.
- 2
Check the length before you upload
One file is up to 30 minutes at the most, so an interview of half an hour fits as it is, and a long one is cut into parts by you, not by us.
- 3
Read the words that were spoken
The transcript comes back line by line, with the start and the end time of every line, and with the speakers named when the split of the voices is on.
- 4
Take the text where it is needed
CSV for a table of the lines, Markdown for a post, TXT for a document, DOCX for an editor on Pro. The same words with the same times are in each.
What you get
- TXT
Plain text for an email, a note or a chat
- SRT
Subtitles for video editors and platforms
- VTT
Subtitles for a browser and a website
- CSV
A table: time, speaker, text
- DOCX
A Word document with speakers and times
- Markdown
Text with headings for notes
What comes back from a video in the feed
cut into parts before the upload; the service does not cut it for you
not analysed: only the sound of the file is transcribed
$0: 3 files a day. Pro is $10 a month paid yearly ($120 a year)
The case
A talk in the feed is not a clip
A Reel is a clip of fifteen seconds and everybody knows it. The video that sits in the feed of a profile is a different animal: an interview of half an hour, a review of a product, a talk that somebody recorded once and published. The words of that video are the thing worth keeping, and the length is the thing to plan for.
Tips
Download the video, do not send the link.
Split a long interview before you upload it.
The text on the picture is yours to add.
Name the speakers while the voices are clear.
Questions this page answers
Is this the same as a Reel?
Not quite. A Reel is a short vertical clip; the video in the feed can be an interview of half an hour, and the length decides how it is uploaded and how the text is used afterwards.
What if the video is longer than 30 minutes?
Then it is cut into parts before the upload: one file is up to 30 minutes at the most, and the parts are sent one after another.
Are the words on the picture in it?
No. Only the sound of the file is read, so the text written over the picture is not in the transcript and has to be added by hand if it matters.
What does a rival give on its free plan?
Notta publishes two hours a month with a 3-minute limit per session (notta.ai/en/pricing, read on 21 October 2026). Ours is $0 with 3 files a day, up to 30 minutes each, and asks for no card.
Sources
- NNotta — the pricing page, read on 21 October 2026notta.ai · checked 21 October 2026
Reading: 5 minutesUpdated Transcribsi editorial team
Drop a recording — the text arrives in a minute
Speakers by name, a time on every line, export to TXT, SRT, VTT, CSV and Markdown.
3 files a day up to 30 minutes, free99+ languagesSpeaker separation and timestamps