My workplace is seeking to expand our video content out to multiple languages. My job is to direct/shoot/edit the English studio video into an exported .MP4, and host it on our HTML5 video player. My boss stated that if we had a VTT subtitle file, that can be overlayed on top of the video without forcing me to bake-in the subtitles onto the original video.
So that boils down to my question: Is there speech recognition software out there that automatically transcribes the spoken word into an exportable VTT text file? Yes it won't be 100% accurate, but will save me from writing in the time-codes and I'll only have to fix whats broken instead of transcribing every bit of spoken word. I'll hand the VTT file off to my programming buddy and he'll work his magic after that.
Any help appreciated. Thanks all.
So that boils down to my question: Is there speech recognition software out there that automatically transcribes the spoken word into an exportable VTT text file? Yes it won't be 100% accurate, but will save me from writing in the time-codes and I'll only have to fix whats broken instead of transcribing every bit of spoken word. I'll hand the VTT file off to my programming buddy and he'll work his magic after that.
Any help appreciated. Thanks all.
