Forum Discussion
Voices and Text-to-Speech - Where ARE we?
So, for those of us not using AI (yet), we need to place emphasis on certain words over others. For example:
- Where ARE we? vs
- WHERE are we? vs
- Where are WE?
I cannot find a way to use emphasis on a particular word using the Neural voices, such as Ruth, Matthew, and Stephen.
I contacted Articulate support, but that did not pan out, as this functionality is not working on these voices. If I'm wrong, please post the SSML code here!
Does anyone have a solution to this need?
Thank you!
3 Replies
Hi, Have you tried something along the lines of the following text-to-speech input:
- WHERE? are we.
- Where are. WE?
- Where, -ARE? we.
Frustratingly, the delivery does change depending on the voice used. Neural Stephen and Danielle have performed the 'best' in my experience.
If editing the tts fails, and neural (or AI) is a must, an audio editing software might be the way to go, e.g. Audacity among others. Or, a t-t-s generator like https://elevenlabs.io/ There are a ton more options out there, some free, some paid. Unfortunately, in my experience, all Neural/AI tts offerings to date (paid and free) are a work-in-progress and all need some fiddling around with before the files are passable.
If you don't have it, here is a link with a list of supported and unsupported tags for Articulate Standard and Neural tts voices: SSML supported and unsupported tags
Thanks, Ange. We are limited, as we don't have the AI function. Regardless, it is a challenge either way. What we need to make it work is not supported by any of the Articulate selections at this time. We need more! 😀
Hi BarbaraJacobs-1,
Thanks for reaching out!
I'm happy to see Ange was able to answer your question. SSML tags work for most standard voices, whereas neural voices have fewer tag options. Currently, neural voices don't support emphasizing words. We'll let you know if this changes!
