consider the ability for the audio story to be updated based on the transcript being manually edited. Look into Elevenlabs.
verbatim “So far so good, however, when I edit text it would be great if the “voice” matched it when I’ve finished editing, instead of keeping the original voice. For example,
Voice says “testing one, two, three, four”; I then delete the text word “ four”, when I play back the voice it still says, “ testing one, two, three, four” Not “testing one, two, three”
As Edited.
Therefore as stories/voices are added to and perhaps edited in the Text, when played back the “Original Voice” is Kept. Which over time May vary more from the Original Story.”
