When I use Text-to-speech and select "generate captions" the cues are often one or two words off. I'm not sure why this is happening when text-to-speech is taking already grammatically formatted text - shouldn't it be able to recognize punctuation as complete phrases? Would appreciate any tips or advice on how to make this work, so I don't have to edit every single closed caption that is generated. (The sentences aren't very long either!)
Thanks for reaching out and sharing what you are experiencing with your project.
The closed captions editor will automatically analyze the audio track to detect units of speech and add caption placeholders to the timeline. Timing adjustments may be needed.
I look forward to hearing if anyone in the community has nailed down a good workflow for this to help you.
1 Reply
Hello Beth and welcome to E-Learning Heroes 😊
Thanks for reaching out and sharing what you are experiencing with your project.
The closed captions editor will automatically analyze the audio track to detect units of speech and add caption placeholders to the timeline. Timing adjustments may be needed.
I look forward to hearing if anyone in the community has nailed down a good workflow for this to help you.
This discussion is closed. You can start a new discussion or contact Articulate Support.