How do I add or edit text-to-speech clips?

Creating new text-to-speech items

1) Click a character and select Dialog in the toolbar.

2) Click Add Dialog to open the menu and select Text-to-Speech.

3) Select a language and a voice from the menu.

4) Type your text in the box and click on the robot symbol to generate the clip.


Editing existing text-to-speech items

1) Right click on the text-to-speech clip in the timeline and select Settings.

2) Click the Edit icon in the text-to-speech modal.

3) Select a new language and/or voice from the menu (if needed).

4) Edit the text in the box and click on the robot symbol to regenerate the clip.


List of available text-to-speech languages

Arabic, Catalan, Chinese, Czech, Danish, Dutch, English, Esperanto, Finnish, French, Galician, German, Greek, Hindi, Hungarian, Icelandic, Indonesian, Italian, Japanese, Korean, Norwegian, Polish, Portuguese, Romanian, Russian, Spanish, Swedish, Thai, Turkish, and Welsh (last updated - April 26, 2019).


Other tips and considerations

When typing text in a specific language, make sure to use the appropriate alphabet - for example, if typing in Russian, use the Cyrillic alphabet in the TTS field.

The text-to-speech engine is sensitive to accent marks (e.g: á, ê, ī). In order to guarantee a correct pronunciation, make sure the text has the appropriate accent marks if applicable.

Here are some other useful tips:

  • Add "fake" punctuations for the TTS voice to mark pauses (e.g: add "," for a short pause and "." for a longer pause).
  • Use "phonics" to write words that are not part of the dictionary (e.g: for the engine to pronounce "Gigya", write it as "guee gya").
  • Split the dialog into smaller parts of 10 words or less. For example: 
    "The Economic Framework is a set of decision rules that align everyone to the financial objectives of the solution and guides the economic decision-making process"
    1) "The Economic Framework is a set of decision rules"
    2) "that align everyone to the financial objectives of the solution"
    3) "and guides the economic decision-making process"

Note: No TTS provider is able to automatically provide the correct voice cadence or tone desired, and some tweaking is usually necessary.

Was this article helpful?
6 out of 7 found this helpful
Have more questions? Submit a request


  • How do I add new voices that are not in the Vyond database?

    Comment actions Permalink
  • Hi first01,

    We've created a support ticket on your behalf and our support team will follow up with you directly; however, in short, our text-to-speech options are managed by third party providers, so we don't have much control over voices. We're happy to pass feedback along to those providers if you're looking for other voices - let us know in the support ticket and we'll take care of you there.


    Comment actions Permalink
  • Hi Cody, any chance of more development of the text to speech? We find it very useful (and fun) but many of our staff don't like them as they are still too robotic. Could there be more control over phonetics? Captivate provides in line coding to set the pace and emphasis of words and syllables - perhaps something like that? Also any chance of those languages and accents being in both male and female?
    Thanks, Steve

    Comment actions Permalink
  • Hi,

    May I know how to change the duration of text-to-speech dialog?
    Thank you.

    Comment actions Permalink
  • Hi Steven,

    We love text-to-speech and have fun with it as well, especially when we are scripting out new videos and using it as a placeholder for real recordings. We prefer to use our own voices when creating tutorials or sending videos in our newsletters, and we recommend our customers do the same, since text-to-speech usually isn't as relatable as a real human voice. Who knows - maybe one day we won't be able to distinguish text-to-speech from a live recording of someone? Or maybe it's already happening! I digress..

    We don't have direct control over text-to-speech development since we use third-party providers. If the voices were developed in-house, we would have the ability to implement your enhancements directly; however, I can pass your feedback along to our contacts at those companies in hopes that they make improvements in the future.

    As for your request for male and female voices, we do have both options in many languages today. For example, Grace and Alan from Australia, Emma and Hugh from the United Kingdom, and so on.

    As our third-party providers release new voices and languages, we'll be sure to include them in Vyond Studio so you can find ones that fit your purposes a bit better.

    If you have any other questions, feel free to send us a message at and we'll help you out there. Thanks!


    Comment actions Permalink
  • Hi Quanxin,

    We've created a support ticket on your behalf and our support team will follow up with you directly. A few tips that I can provide here in the meantime:

    - Use commas to add pauses within the text-to-speech editor
    - Add line breaks if you need more spacing within groupings of words
    - Create separate text-to-speech tracks if there are large gaps with silence, or so that you can move the audio clips around in more of a granular way in the timeline

    We'll follow up with you via email with some more information and discuss more about what you're attempting to accomplish with text-to-speech. Chat then!


    Comment actions Permalink

Article is closed for comments.