Floik: Generate AI voiceover from element
backlog
C
Claus Schittenhelm
I want to use AI voiceover to just read out loud the text I enter in elements like "hotspot" and "text". Therefore, instead of only a field to manually enter the voiceover text, I could imagine an option "Use text from element". This is similar to what tools like Synthesia or HeyGen do.
Log In
C
Claus Schittenhelm
Hi Kavya, thanks your quick response! I was experimenting with an interactive demo, and when I added AI Voiceover, I was a bit surprised that I had to enter the text from the hotspot again. I think a toggle would be great, where you could opt if you want to use the same text as in the hotspot, or use a different narration. Another thing I noticed is that when you add voiceover to a text element, it does not sync with the video like it does for hotspots. Basically, the voiceover for a hotspot is played in full, but if I add voiceover to a text element, the video keeps playing and the voiceover may run over. Does that make sense? Thanks! Claus
D
D360 Product Management
marked this post as
backlog
K
Kavya
Hi Claus Schittenhelm,
Thanks for the suggestion! Automatically using the text from a hotspot or text element for the AI voiceover would definitely streamline the workflow, and we can see how this would be helpful—especially for demos with lots of narrated steps.
This isn’t something that’s on our roadmap right now, but we’ll keep an eye on interest and let you know if we move forward with it.
To understand your needs better, could you share a bit more about how you’d expect this to work?
Would you want the voiceover to always pull from the element text automatically, or only when you enable a toggle?
Are there situations where you wouldn’t want the voiceover to read the element text?
Your input will help us evaluate what the most helpful approach could look like.