Text-to-Speech TTS service
Text-to-speech allows the creation of sound files using computer-generated voices to read out your chosen written text. This service has been around for many years, however when a text-to-speech (TTS) service was generated, it sounded very robotic. This made the service poor to use in a commercial environment for services on a telephone system. TTS has progressed and improved over time. We now have very natural-sounding computer-generated voices that are more realistic. You can test this by listening to your recordings before they are purchased. Under features, go to the Text-to-Speech tab.
At the bottom right, there is a new button. Click this to create a new audio file
Name
Give your new recording a name that will help you remember what it is
going to be used for. Something like ‘Main greeting.’
Description
If you think you may need more details, enter them here.
Available voices
|
|
This is your choice of voices; there are 12 to choose from. |
Text - This is the area you insert the text you want the service to create your audio file. You can use commas to create a brief pause and full stops to add a slightly longer pause. Either way, we suggest that you type it as you would like it spoken, then, to preview the sound before saving, click ‘Test your audio file’ and hear what it sounds like. (There is a limit of 500 characters).
Once you are happy with it, click save, and your recording will appear in Features > TTS and Features Advanced > Sounds on the portal
Click save, and you will be shown the cost of creating the recording. Click OK to continue. Now you have the audio file saved, which can easily be accessed in various parts of the portal by selecting ‘sound file to use’ and choosing the name of the file you recorded. Located on the TTS Files page (Features > Text-to-Speech) where the recordings are saved, click on ‘Sound’ on the right, and you can download the file. You could also choose to upload another file, similar to how you listen to other sounds on the platform.