Text-to-speech for sentences in two languages

Apr 01, 2020

Dale Hines
By Dale Hines

I have translated a course from English to Spanish.   However, there are a few terms and acronyms that need to said in English.    They naturally appear throughout the sentences.   I have used the text-to-speech functionality to create the audio.  

Here's what I'm doing:  I copy the beginning of the sentence (that's in Spanish) and paste it into the Text-to-Speech dialog box, choose the Spanish voice and click on Insert.   Then I go back to copy the term/acronym (that's in English), paste it into the Text-to-Speech dialog box, choose an English voice and click on Insert.  Lastly, I repeat my first step for the remaining Spanish words in the sentence.

My question is:   Is this the most efficient way to generate the audio with the mix of  Spanish and English in the same sentence?

2 Replies
Ashley Terwilliger-Pollard
4 years ago04/03/20 at 4:45 pm (UTC)

Hi Dale! 

I love that you're thinking about efficiencies to speed up your Storyline workflow. The method you shared is what I would have recommended. 

I'll put the question out the community at large: How do you combine two languages in one Text-To-Speech track?  

I hope there's a language expert out there to weigh in on this and help your projects along.

Thor Melicher
almost 4 years ago04/24/20 at 12:15 am (UTC)

Currently Storyline 360 doesn’t support using SSML (Synthesized Speech Markup Language).  If it did, this would be easy to solve as you would use a tag to say the word with an English accent which also keeps the same voice so it sounds more natural.

For example, 

Mi nombre es Tom Brady would be written as

Mi nombre es <lang xml:lang="en-US">Tom Brady</lang>

With that being said and that Storyline 360 doesn’t support SSML tags, I wrote an application to help facilitate the process using Amazon Polly directly (which is what Storyline uses): 

  1. Get an Amazon Polly account (yes, there is some cost involved but doesn’t seem that prohibitive) (https://aws.amazon.com/polly/)
  2. Save your scripts as separate files (MS-Word or Text)
  3. Download HeroVoice TTS from the Microsoft Windows Store (fully functioning 15-day free trial)
  4. Encode your files with HeroVoice TTS – apply a global setting for speed and even comma duration so your files are consistent.
  5. Select the voice you want – these are the same as you’ll find in Storyline today including Neural voices (which aren’t currently available in Storyline)
  6. Load each audio file into Storyline

If you have one file then you probably wouldn’t need to use HeroVoice TTS as you could use the Amazon Polly console to get your file, however, you may also like these other requested features from the Storyline Community:

  • Adjust the overall speed of your files with one setting
  • Adjust the overall pause duration for commas
  • Add your own SSML to get more finer nuanced, naturally sounding results
  • Neural voices
  • Batch process your files

For more information on what else you can do with SSML tags and Amazon Polly, a good reference can be found here: https://docs.aws.amazon.com/polly/latest/dg/supportedtags.html

This discussion is closed. You can start a new discussion or contact Articulate Support.