Solutions to caption speech to text in PT on Monterey

[nednednerb]

Hi there,

Does anyone have a solution working for them to do this?

I see that Ventura on Silicon will have a "Live Caption" feature, but so far I have to rely on cloud transcribe services AFTER editing and exporting audio to get visual text of the content of the speech audio I am working on.

It would be a wonderful thing, with Aux I/O to feed the Keyboard dictation service, but it wants to type into a text document, not simply display the text as a caption in a window or something.

Really, it would be swell if I could load a plugin into Pro Tools, select an audio clip, and in a second or two for short clips I could visually confirm the speech content of the file by looking at a text displaying plug-in window on my other display or bottom of primary display.

It LOOKS like Media Composer might be able to do something like this, but the feature is not present in PT. Does anyone know about that? I might contact sales, they will be keen to inform me hah!

In general, what do other people working on dialogue/voiceover do in order to "see" and not only "hear" the speech content they are editing? I have a source document, but a solution to my issue would be nice.

Edit: Hmmm, I see it also looks like RX10 has a "text navigation" feature. As I already use RX, doing more standalone editing in RX before I port to PT for other edits MIGHT be a workable solution for me to get this in my workflow, but a PT Speech-to-Text viewer would be a nice-to-have!

[its2loud]

It’s not a plug-in and doesn’t work inside Pro Tools but check out Descript. It might provide some assistance for what you need to do