1
00:00:00,100 --> 00:00:04,725
Every word in this recording has a timestamp,
captured by the speech engine at the

2
00:00:04,725 --> 00:00:05,925
moment it was spoken.

3
00:00:06,263 --> 00:00:10,701
Nothing was estimated from the text, and
nothing was recovered by transcribing the

4
00:00:10,713 --> 00:00:11,913
audio afterwards.

5
00:00:12,225 --> 00:00:16,838
That is why the subtitle file next to this
one lines up exactly, without a single

6
00:00:16,850 --> 00:00:18,050
manual adjustment.