I have a file with text, typically about 2 paragraphs long. I am looking to create a video where the audio is text-to-speech and the visual is simply the text that is currently being spoken, say, about one sentence at a time.
This would need to be a lightweight process. Ideally this would be as simple as uploading the text file, choosing a voice, and clicking a process button.
However, I am having trouble finding a software application that will both create the audio and semi-animated text from the text file in a simple fashion. It seems relatively easy to find text-to-speech services or to find subtitling, separately. But creating a video of just subtitles based on interpretation of the audio from an original text source seems unnecessarily clunky.
What are my options here?