Forum Discussion
Problem with automatically generated subtitles ?
Hello StevenBenassi
Thank you for your reply. I am happy to send you an extract from one of my .story files (a few screens) that I have annotated for clarity. But I am almost certain that it is not my files that have a problem, but rather Storyline in this regard.
I can confirm that the subtitles are never “aligned with the natural pauses in AI-generated audio or Text-to-Speech.”
What I discovered today is that if the “Generate subtitles” box is unchecked, then the subtitles, although visible in the subtitle editor, do not appear on the screen. OK. But if I want to make them appear after all, by checking the box, I get disorganized subtitles every time.
I know there are workarounds. Export/import neatly arranged subtitles.vtt. Cut the voices into several pieces so that you only have to rework ONE sentence if you need to change ONE word (but we know that the quality is better when the voice says an entire paragraph, not just one sentence.)
But there's something impractical about it.
The expected logical behavior would be (in my opinion): 1) Subtitles aligned with natural pauses in the voice. 2) Automatic creation and modification of subtitles SUSPENDED when the “Generate subtitles” box is unchecked. 3) Manual arrangement of subtitles
RETAINED if the box is unchecked 4) Differentiation between the two functions: “Generate subtitles” and “Display subtitles.”
Please don't forget: why do I insist so much on being able to keep manual changes? In French (and many other languages!), subtitles need to provide additional nuance. For example: the voice + subtitles say “Ready?”. In French: “Prêt ?” But if you're addressing a woman: “Prête ?” (with an e). And to several people: “Prêts ?” (with an s). So, to address everyone, and to be quick, I'll write “Prêt(e)(s) ?” in the subtitles. This is allowed. But I would lose this work every time I modified the voice prompt. There are dozens of examples in French. Hundreds of examples if you count other languages.
Thank you in advance.
A new thought occurred to me this afternoon, dear StevenBenassi.
On my latest project, my client asked me to change the AI voice on the finished module, without changing the text. I would have liked to be able to keep the precise re-cutting of all my subtitles by changing only the voice!
And one last thing before I go for a nap: as you can see in my file, my prompts have lots of line breaks to force the voice to pause where I want it to, since SSML tags don't work with AI voices (am I right?). This may also prevent the subtitles from aligning properly with the “natural” pauses in the AI voice.
Hi ThierryEMMANUEL!
Thank you for following up and providing such detailed feedback!
I can definitely see how these behaviors create extra steps for you while working with AI-Assisted Text-to-Speech in Storyline. I've included your voice in the two Storyline bugs that are currently being tracked:
- Closed Caption Editor shows captions even if authors opt out while generating TTS
- Generated Closed Captions' placeholders do not align with the natural pauses in AI-generated TTS
Also, I'd like to touch upon your point regarding changing an AI voice in an already completed project. I tested this with a TTS element on Slide 1.2 in your .story file. Switching the voice from Danielle to Matthew, I did not notice changes with the format of the captions or issues with the playback during preview. If you're having a different experience on your end, seeing a screen recording of that issue would be helpful!
Regarding SSML, AI Assistant's Text-to-Speech feature does offer some SSML support, but it's limited compared to our classic TTS. The AI-Assisted TTS supports the '<break>' tag for manually controlling pacing, but it does not support SSML phoneme tags which can make indicating speech terminology more challenging. If you require full SSML support, the classic TTS feature would be the better choice for now. I've shared your feedback on this limitation with our product team as well.
Looking forward to hearing from you!
