Forum Discussion
New Text to Speech Feature in Articulate Storyline 360
I am very excited at this new feature. It seems to use the Amazon Polly engine to do it's conversion. I would like to know if there is a way to edit the text to speech to slow it down, add emphasis, and customize it like you can do in Polly with SSML tags. The speech is great it is just a little quick for what I will need it for in my course development.
Hi, everyone!
I have some great news to share. We just released another update for Storyline 360. In Update 83, we've included important fixes and new features!
One of the new features we've included:
- Unlock new possibilities for text-to-speech audio. Use speech synthesis markup language (SSML) to adjust the speaking rate, modify pronunciation, emphasize words, add pauses, and more.
Launch the Articulate 360 desktop app on your computer to take advantage of this update, and click the Update button next to Storyline 360. You'll find our step-by-step instructions here.
Please let me know if you need additional help!
28 Replies
This is a great question Chris! I am not sure, but there doesn't seem to be at the moment.
It wouldn't surprise me if this was coming next though. When they released the CC features, the ability to import CC files was released first, and the CC editor came soon after.
You could also request a feature here: https://articulate.com/support/contact/feature-request
Thank you Veronica. I did submit a feature request. I will continue to use Polly until there is a way to change it or the speed of the speech doesn't detract from my courses.
I think I might have found a work around to get TTS captions and use my Polly audio files. Will post more later.
Sound good Chris, and would be super if you could update the thread, a lot of people will find this useful.
Do the Articulate 360 TTS engine support Speech Synthesis Markup Language (SSML) to provide more user control like paragraph, breaks and audio pause etc to customize the audio creation.
Hello SibaPrasad! Check out this tutorial on using the text to speech feature. You can make changes to the text or to the voice, presently.
It sounds like it would be a popular feature to have more robust editing capabilities of the narration that's generated; let us know what works for you in a feature request!
+1 to adding the ability to use SSML tags.
Just to make sure I got everything right: there is no way to edit text-to-speech in order to insert pauses inside paragraphs or phrases, am I right?
I tried filling the text with dots or commas but nothing changes, and working with Silences is very time consuming, since there is no way to rapidly preview a slide during audio editing.
That's a pity: the tool could be useful but as it is, IMHO, it seems quite uncomplete and difficult to use properly.
Hi Nicola!
I typically recommend adding extra punctuation within the text, or manually adding silence to the narration in the Audio Editor. It sounds like you've already tried those options and you're looking for something more user-friendly. We're tracking these requests, and we'll definitely let you know if more editing tools are added to the text-to-speech feature in the future!
Hi Alyssa,
and first of all thank you for your kind and quick reply. As you mentioned, I already tried adding extra punctuation but it just didn't work: even if I insert lots of dots or commas, pauses last the same. Should I use something else?
In ended I worked with silences in Audio editing and I managed to get the text how I wanted it, but it really takes a lot more time than working with tags or similar.
I hope you'll add a specific tool in the future since it doesn't seem that difficult to me!
I vote for tags also. It seems reasonable that these could be added since the voices in 360 are from Amazon Polly, where you can control the speech.
Adding silence and manipulating the audio sounds more unnatural than using the built in SSML tags that work with Polly. Yes this may not sound as user friendly as some audio editor, but the tags are easy to use once you get hang of them and a system that allowed you to drop in specific tags would make manipulating the speech must quicker and give you a better control of how the speech sounds. This is similar to allowing users that can write JavaScript to use it and there should be a way to mark up the speech for those that can use tags.
Hi Nicola,
I'm glad you were able to add in the silences, and as Alyssa mentioned we're sharing all the experiences and feedback here with our team. We'll keep you posted on any new features for Text to speech!
Is there a way to slow down the speech speed? I am a new user here and I may be missing where that function may be located.
