Only the sound is used
The picture is skipped: the speech model hears only the video's sound. While you check the text, each line shows over the picture at its time, the way subtitles will look in a player.
Saved as SRT or VTT, the lines carry their start and end times, and YouTube takes both as a subtitle file next to the video. To put the words into the picture itself, so they show on every app, use Add Subtitles.
Videos with more than one sound track
The model hears the video's first sound track. If yours has a second language or a commentary on another track, save that track as an MP3 with Video to MP3, where you can pick it, and choose the MP3 here. The times still match the video, since both start at the same moment.
Which file to save
| You want | Save |
|---|
| To read, search or paste the words | TXT, or Copy |
| To send it to someone or edit in Word | DOCX |
| A page to print or attach | PDF |
| A subtitle file for YouTube or a player | SRT or VTT |
- To read, search or paste the words
- Save: TXT, or Copy
- To send it to someone or edit in Word
- Save: DOCX
- A page to print or attach
- Save: PDF
- A subtitle file for YouTube or a player
- Save: SRT or VTT
What goes to our server
Only the sound goes to Snipmill's server, when you press the button that starts the job; the line under it says so. The server deletes it once it has answered and keeps no copy. The page reads the recording and makes its sound small; a video's picture isn't sent. The text comes back to this page, and only you decide where it is saved.