Removes timestamps from a transcript in your browser: paste the text or drop a .txt, .vtt, .srt or .docx from YouTube, Zoom, Teams, Google Meet, Otter, Loom or Word. Cue numbers go too, while speaker labels and filler words are your choice. Rules do the work, not AI rewriting. Copy the result or save it as .txt or Word. No account, no daily limit.
Drop a .txt, .vtt, .srt or .docx — or paste the text
Cleaning runs in your browser. The file is not uploaded.
Two lines per source, from each vendor's own documentation and public samples. Checked ; vendors change their files, so the cleaner reads what it finds rather than what the page promises.
Open the video, expand the description, press "Show transcript" and copy the text from the panel.
The cleaner drops the times, including the spoken "1 minute, 5 seconds" lines that can come with them.
Remove timestamps from a YouTube transcriptHow to get a YouTube transcript
The cloud recording keeps an audio transcript as a .vtt file: numbered cues, a time range per cue and "Name: text".
The cleaner drops WEBVTT, the cue numbers and the time ranges, and keeps the names unless you remove or rename them.
Zoom: audio transcript for cloud recordingsZoom transcript to textZoom meeting transcripts
After the meeting the transcript downloads as .docx or .vtt, by default for the organizer and co-organizers.
The cleaner drops the times, the cue ids, the "started transcription" lines and the panel's doubled screen-reader text.
The transcript is a Google Doc in the organizer's Drive, in the "Google Meet" folder, one "Name: text" paragraph per utterance.
The cleaner drops the five-minute markers, the "computer generated" notice and the closing "Meeting ended after" line.
A .txt export puts each speaker and time on one line, the paragraph under it, and a footer line at the end.
The cleaner drops the times and the footer, and joins turns of the same speaker if you ask it to.
Open the video's transcript and copy it; downloading an .srt file needs a Business or Enterprise plan.
The cleaner drops the leading times and joins the short lines into paragraphs. Loom transcripts carry no speaker names.
Loom: video transcription and captionsLoom video transcripts
Word's Transcribe can add the text to a document as just text, with speakers, with timestamps, or both.
Any .docx works here: the cleaner reads the paragraphs, drops a leading time and a "Speaker N" label, and writes a clean .docx back.
By hand, the empty lines and the spaces the times leave behind stay. The cleaner tidies them and keeps one paragraph per turn.
[0-9]{1,2}:[0-9]{2}:[0-9]{2}[0-9]{1,2}:[0-9]{2}Speaker [0-9]{1,}\d{1,2}:\d{2}(:\d{2})?Speaker \d+:?Input — a Zoom cloud transcript (.vtt), cue numbers, times and a name on every line
WEBVTT
1
00:00:02.350 --> 00:00:05.120
Maya Ortiz: Okay, let's get started.
2
00:00:05.400 --> 00:00:09.880
Maya Ortiz: First item is the launch date.
3
00:00:10.210 --> 00:00:12.040
Daniel Kim: We moved it to the 14th.
Output — timestamps removed, speaker names kept, one paragraph per turn
Maya Ortiz: Okay, let's get started. First item is the launch date.
Daniel Kim: We moved it to the 14th.
Same file with Speaker names set to Remove — the paragraphs stay
Okay, let's get started. First item is the launch date.
We moved it to the 14th.
Paste what you copied, or drop a .txt, .vtt, .srt or .docx. The page recognises where it came from — YouTube, Zoom, Teams, Google Meet, Otter, Loom or a Word document — and shows it in one line you can change.
Timestamps are removed by default. Speaker names can stay, go or be renamed ("Speaker 1" to "Anna"), lines of one speaker are joined into a paragraph, and filler words such as um and uh can be taken out. Cue numbers and file headers are always removed.
The first lines show at once, with a count of what was removed. Change an option and the text changes with it; nothing needs a Clean button.
Copy the text, save it as .txt, or save a Word document with the speaker names in bold. If you want the summary and action items of a meeting, one more click sends the cleaned text to write them.