Techniques are presented herein that support automatically updating the spoken words in a video presentation (using a custom text to speech (TTS) model that is tuned to the video creator’s own voice) that contains dynamic content whenever that content changes. Aspects of the presented techniques employ a cataloging mechanism, an image-to-text machine learning module, and a natural language processing (NLP) data labeling mechanism. Further aspects of the presented techniques offer an end-user interface that allows a user to select and verify which portions of the dynamic content should be automatically updated whenever a change is detected.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.