How does the Video intelligence splits an audio into transcripts [183691912]

Fixed

Bug

Status Update

No update yet.

Description

ma...@google.com

created issue #1

Mar 25, 2021 11:24AM

A customer had an inquiry regarding the Video Intelligence transcripts. Currently, it seems the API splits an audio into transcripts of roughly 50 to 60 seconds chunks. However this information is not in the documentation. Could you please clarify/mention it within the Video Intelligence documentation?

Comments

ut...@gmail.com <ut...@gmail.com> #2Apr 5, 2021 10:09PM

Is there any update on this ?

se...@google.com <se...@google.com> #3Jun 4, 2021 03:35PM

Assigned to gc...@google.com.

Hello,

Product team is working and evaluating this case. Once there will be information, it will be shared in this thread.

Kind Regards

wi...@google.com <wi...@google.com> #4Apr 9, 2024 08:52AM

Marked as fixed.

Hello,

Documentation has been updated to contain more detail about this feature https://cloud.google.com/speech-to-text/docs/speech-to-text-requests

Best Regards

Issue 183691912

Description

Issue summary

Comments

ut...@gmail.com <ut...@gmail.com> #2Apr 5, 2021 10:09PM

se...@google.com <se...@google.com> #3Jun 4, 2021 03:35PM

wi...@google.com <wi...@google.com> #4Apr 9, 2024 08:52AM

Add comment

Issue metadata