Paste a transcript from tl;dv, Zoom, Teams, Google Meet or a VTT/SRT caption file. You get back clean, speaker-labeled text that is ready for ChatGPT, Claude, NotebookLM, Notion or a doc. It runs 100% in your browser, and nothing is uploaded.
Need every transcript, not just one? MinuteHaul exports all your tl;dv meetings into one ZIP (Markdown per meeting + CSV index + one combined file for ChatGPT). Try it free on your 10 most recent meetings or pre-order unlimited: $29 one-time.
No. The cleaner runs entirely in your browser with JavaScript. The text never leaves your device.
Lines like "Name: text", "[00:01:02] Name: text", "Name (00:01:02): text", a timestamp-plus-name line followed by text, and WebVTT/SRT captions (including <v Speaker> tags). Anything else is kept as plain text.
It is a rough estimate of 1.33 tokens per word. Real token counts depend on the model's tokenizer and the language.
Yes, as long as the transcript is plain text or VTT/SRT in one of the formats above. It is not tied to any one meeting tool.
Only um, uh, erm, hmm, uh-huh and mm-hmm. Words like "like" or "you know" are kept because removing them can change meaning.
Related: tl;dv transcripts in ChatGPT, in Claude, in NotebookLM, to Markdown.