This App will take a video and use voice recognition and google images to overlay an image every couple seconds which reflects what the person is saying.
After further research i'm no longer planning on using python for the backend and will just use javascript with Fluent-ffmpeg library
Check out the Trello board
- UI will be made using my presonal build of electron
- Need to develop system for getting images for video using speech recognition.
- Write or Adapt script for downloading the images based on script and config.
- Stich images and video together according to settings which will be placed in UI.
- Voila!
- No Transcription service is free forever :(