I've just written a new free tool that I want to share, Batch WhisperAI. Here's the current dialog.
It stems largely from this thread https://www.vegascreativesoftware.info/us/forum/speech-to-text-via-whisper-openai--137928/?page=1
and a specific request by @bitman https://www.vegascreativesoftware.info/us/forum/speech-to-text-via-whisper-openai--137928/?page=1#ca863446 and also my need to quickly create a text file from lots of audio recordings that I had made earlier this year documenting my road trip to Alaska.
Here is a DropBox link where the app may be downloaded which also includes the WhisperAI models and instructions for installation. https://www.dropbox.com/sh/qpjskuyq6bw6i2f/AAAjKPuBid2ggK2gzh4z29Nka?dl=0 For those with an Nvidia card, the app automatically selects GPU rather than CPU processing. Note that GPU processing is available only for Nvidia cards. Just make sure that you download and install the required Cuda files. Here is a link to the app, Whisper-faster, that actually does the speech to text processing. https://github.com/Purfview/whisper-standalone-win
And finally, here's a short demo I prepared using some video files I created some years ago. Note that the UHD demo is also available in the DropBox folder and can be downloaded for better viewing.
I will eventually add this tool to the HappyOtter Free Tools Library. Comments and suggestions for improvements are welcome. Enjoy.
The Batch WhisperAI app has now been included in the latest version of HappyOtterScripts. For ease of installation, just run the setup file--no paid license is required. https://www.vegascreativesoftware.info/us/forum/happy-otter-scripts-for-vegas-pro--113922/?page=44#ca891774