I have recently started using Articulate Storyline.
We are trying to find TTS service with neutral English accent (something like UK accent), for our e-learning courses.
I have searched and found that Ivona have pretty good accent but its not for commercial use. So, if anyone is using or have some idea from where I can get it, please let me know.
I have been using Ivona Studio for the past couple of years, and actually had really good success with it (especially considering I could customize pronunciation using ssml tags). However, my voice licenses expires in a few days and upon trying to renew, I was told that they (Ivona) no longer supports these offline products. As a result, I am now in the process of investigating NextUp's TextAloud (which also includes some Nuance voices - that's an added bonus) and ReadSpeaker SpeechMaker (recommended to me by Ivona).
I will be glad to share with you any information I get regarding these 2 products. If you have discovered any other option that you think is viable, I would certainly love to hear!
I have downloaded and tested NextUp's TextAloud (http://nextup.com/TextAloud/) with the Ivona Salli voice (as I still have an active Ivona license until the end of this week). Here's what I found:
Ivona Studio uses SSML for phonetic customizations, but TextAloud does not. They do have a "Phoneme" dictionary which you can use to piece together the pronunciation, for example: "tomorrow" could be phonetically defined as "t uw m aa 1 r ow 2" (where 1 and 2 are the primary and secondary stresses). It may look difficult, but really it is just a matter of sounding out the word and selecting each phonetic sound from the list.
You can load additional voices other than Ivona. If you are using a PC (vs a Mac), Microsoft actually includes a couple of default TTS voices, one being Zira. I played around with an audio file, playing it one time using the Ivona voice and then playing it using the Microsoft Zira voice. Believe it or not, I actually found that I like the *FREE* Microsoft Zira voice better -- to me, it sounded a bit more natural.
We will likely purchase all 5 Ivona voices (though we have predominitely used Salli), as well as the Allison voice from Nuance. At this time, we probably won't invest in the compatible AT&T or Acapela voices, but those are options.
I am attaching a couple of example files that I have created - the audio contents are the same, but one is created using Ivona Salli voice and one is created using the Microsoft Zira voice. The txt file is the script that was used. This will give you an idea of what can be created (in literally a matter of about 5 minutes) using the TextAlound engine.
2 Replies
Siddharth,
I have been using Ivona Studio for the past couple of years, and actually had really good success with it (especially considering I could customize pronunciation using ssml tags). However, my voice licenses expires in a few days and upon trying to renew, I was told that they (Ivona) no longer supports these offline products. As a result, I am now in the process of investigating NextUp's TextAloud (which also includes some Nuance voices - that's an added bonus) and ReadSpeaker SpeechMaker (recommended to me by Ivona).
I will be glad to share with you any information I get regarding these 2 products. If you have discovered any other option that you think is viable, I would certainly love to hear!
Siddharth,
I have downloaded and tested NextUp's TextAloud (http://nextup.com/TextAloud/) with the Ivona Salli voice (as I still have an active Ivona license until the end of this week). Here's what I found:
Ivona Studio uses SSML for phonetic customizations, but TextAloud does not. They do have a "Phoneme" dictionary which you can use to piece together the pronunciation, for example:
"tomorrow" could be phonetically defined as "t uw m aa 1 r ow 2" (where 1 and 2 are the primary and secondary stresses). It may look difficult, but really it is just a matter of sounding out the word and selecting each phonetic sound from the list.
You can load additional voices other than Ivona. If you are using a PC (vs a Mac), Microsoft actually includes a couple of default TTS voices, one being Zira. I played around with an audio file, playing it one time using the Ivona voice and then playing it using the Microsoft Zira voice. Believe it or not, I actually found that I like the *FREE* Microsoft Zira voice better -- to me, it sounded a bit more natural.
We will likely purchase all 5 Ivona voices (though we have predominitely used Salli), as well as the Allison voice from Nuance. At this time, we probably won't invest in the compatible AT&T or Acapela voices, but those are options.
I am attaching a couple of example files that I have created - the audio contents are the same, but one is created using Ivona Salli voice and one is created using the Microsoft Zira voice. The txt file is the script that was used. This will give you an idea of what can be created (in literally a matter of about 5 minutes) using the TextAlound engine.
Hope this helps!
Bobbi
This discussion is closed. You can start a new discussion or contact Articulate Support.