Transcribe a TikTok video to text
Transcribe the sound of a TikTok clip: upload the file, get a timecode on every line and the words of the voiceover written out. Free $0, 3 files a day.
Upload the sound of the clip and the transcript comes back with a timecode on every line and the words of the voiceover written out. One file is up to 30 minutes, the free plan is $0 with 3 files a day.
How to transcribe the sound of a TikTok clip
- 1
Save the audio of the clip
Keep the file you have the right to keep: your own clip, or a file that was sent to you. The service does not download anything and has no TikTok integration.
- 2
Upload it on the widget
Drop the file on the widget above. A clip is far below the limit of up to 30 minutes, so the upload is refused only if something is wrong with the file.
- 3
Read the words with the times
Every line carries the time it starts and ends, so a quote can be checked against the clip in a second, and the voiceover can be cut out of the transcript.
- 4
Export for the caption file
SRT and VTT for the clip, TXT for the notes, CSV for a spreadsheet, DOCX for an editor on Pro. The timecodes are the same in all of them.
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 the sound of a clip
- A clip
far below the limit of one file: up to 30 minutes on the free plan, no minute limit on Pro
- The words of a clip
one line per segment, with the time it starts and ends
The words in a clip are often the point
A TikTok clip is short, and the words in it are often the point: a recipe said out loud, a joke with a punchline, a line that has to be quoted somewhere else. The sound of the clip is what carries them, and the sound is a file like any other. Save the audio of a clip you are allowed to keep, and the transcript of it is a minute of work.
Tips
Save only the clips you have the right to keep.
The picture of the clip is not needed for the transcript.
A clip is short: the free plan is enough for a batch.
Export SRT when the clip has to be captioned again.
Questions this page answers
Can the service download a clip by link?
No. There is no link field in the app and no TikTok integration in the product: the service reads files. Save the audio yourself and upload the file.
Do I need the picture of the clip?
No. The transcript is built from the sound; the picture is not read at all. Upload the video file as well and the same words come out of it.
What if the clip is in another language?
We support 99+ languages, and a mix of the two. Leave the detection on and the service picks the language from the first lines of the audio.
Is an editor the right tool for this?
Not for the words. Descript, an editor with transcription inside it, starts at $16 a month paid yearly (descript.com/pricing, read on 21 October 2026); it is the tool for cutting a clip, not for writing its words down.
Sources
- DThe pricing page of Descript, read on 21 October 2026descript.com · checked 21 October 2026
Reading: 4 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.