TXT or SRT: which format do you need?
- TXT: plain text, optionally with [mm:ss] timestamps. Best for notes, quotes, articles and AI tools like ChatGPT.
- SRT: numbered subtitle blocks with start and end times. Best for Premiere Pro, DaVinci Resolve, CapCut, Final Cut, VLC and re-uploading captions.
- VTT: the web subtitle format. Best for HTML5 video players and online course platforms.
Download YouTube subtitles without software
YouTube lets you view a transcript, but not download it. Copying it by hand loses the formatting and mixes timestamps into the text. Summ gives you a clean file in one tap on your phone, and videos already in our library can be downloaded as TXT or SRT right on this page.
Tips for working with downloaded transcripts
- Turn timestamps off before copying into a document or an AI chat. The text is cleaner and uses fewer tokens.
- Keep timestamps on when you're making notes, so you can jump back to the source moment.
- Auto-generated captions don't have punctuation. Paste the text into the Summ app to get a readable summary instead of a wall of text.




