Forum Discussion
Text-To-Speech on All Slides at Once
Learning this is surprising. It definitely slows down the workflow. I hope you address this one quickly!
Hi, ricks1! Thanks for adding your perspective. It sounds like generating Text-to-Speech slide by slide is slowing down your workflow as well.
I'd love to learn a little more about your experience. Approximately how many slides do you typically generate Text-to-Speech for in a project, and how much time do you think a bulk generation option would save you?
Learning more about the scale of your projects helps us better understand where a capability like this could have the greatest impact.
My current project.
My last narrated project, using external narration files, was nearly 200 slides.
Yes, I know this is too much information in a single course, but I don't always hold sway over course length.Thanks for sharing that context, ricks1! A project with nearly 200 narrated slides really helps illustrate the scale of the workflow and the amount of repetitive effort involved today.
I also appreciate you mentioning that course length isn't always within your control. That additional context helps us better understand where a bulk Text-to-Speech capability could make a meaningful difference.
I’ve been using Articulate a long time and I appreciate your speedy reaction and reply. You’ll have to excuse me for being a bit of a pessimist, having seen many great ideas for feature requests languish for years.
Hi EricSantos! I would like to jump in here as well and provide my two cents. Here's our workflow and why bulk audio generation and global pronunciation corrections would be a valuable enhancement:
Our typical process:
We frequently import PowerPoint files into Storyline, and the slide notes come in with them. These notes serve as our narration transcript. Currently, we have to touch every single slide individually, not just to update triggers, states, and variables, but also to generate audio.Current per-slide audio workflow:
Even with AI Assistant, the process for each slide is:- Click "Insert Audio"
- Click "Add from Slide Notes"
- Click "Generate Voiceover"
While three clicks per slide isn't terrible, multiply that across a 30-slide lesson and it adds up.What bulk generation would enable:
If we could generate voiceovers for all slides at once, after all notes are imported/added, our workflow would shift from:- Add audio → Listen → Update (if needed) → Move to next slide
To:
- Generate all → Listen and update only where needed
This would save significant time and reduce the context-switching between building and audio generation.Additional suggestion - Global pronunciation corrections:
One challenge we run into: when a voiceover mispronounces a term (for example, saying "I.C.E." as three letters instead of "ice" as one word), we currently have to catch and fix it on every slide where it appears. It would be incredibly helpful if pronunciation corrections could be applied globally across a project; fix it once, apply everywhere.Approximate scale:
Our typical projects range from 15–50 slides per lesson. Bulk generation would have the greatest impact on our larger lessons and multi-lesson courses where we're generating hundreds of audio clips.
