undefined | Better HN

0 pointssho_hn3y ago0 comments

1. Prompt it to extract the audio track, then give it to a speech-to-text API, translate it to another language, then make it add it back to the video file as a subtitle track.

2. Retrain the model to where it does this implcitly when you say "hey can you add Portuguese subtitles to this for me"?

0 comments

stnmtn3y ago

I don't have words for how much this seems like a relatively trivial thing to do now, and 1 year ago I would have laughed at someone if they suggested this was a possibility in 5 years

I'm feeling a mixture of feelings that I can't begin to describe

sho_hnOP3y ago

The Star Trek computer is here! :-)

JaDogg3y ago

But not the Star Trek economy / elimination of money. So some of us will starve while we get there. :(

TechnicolorByte3y ago

Well said. It so easy to take for granted all these tech milestones with generative AI in particular the last year.

iamwil3y ago

"Falling forward into a future unknown"

stevenhuang3y ago

no retraining may be necessary, this is a common enough ffmpeg task I wouldn't be surprised it can do it right now as a one-shot prompt.

what a time to be alive!

swyx3y ago

holding on to my papers fr fr

ManuelKiessling3y ago

You mean like this?

https://app.fyyn.io/en/features#element-10

j / k navigate · click thread line to collapse