Text-to-Speech allows you to generate a sound file from the text entered. This is inserted into Timeline as a sound object.

You can find the effect in the Toolbox under the Objects tab in the Audio section.

Drag the Text-to-Speech object from the Toolbox to the Timeline to the position where you want a comment to be spoken.

The Text-to-Speech dialog opens.

Select the voice with which you want your text to be spoken.

You can choose from

- from the desktop voices supplied by Windows for the voice output.

- optional voices from Google Gemin (with your own connected Google account)

- optional voices from ElevenLabs (if an own API key has been stored)

Use the cogwheel icon to access the recording settings for differentiating the sound settings (e.g. mono/stereo) and the Account settings for connecting with Google or ElevenLabs in the Program settings.

Select a Target file and the directory in which the sound file is to be saved.

Enter the text to be spoken in the text field.
 
Voices from Google and ElevenLabs can be modified via prompt input. Enter instructions such as "Narrate excitedly and quickly", "Speak in the style of a storyteller", "Speak in Bavarian dialect and always emphasize the word Oktoberfest", "Shout the text".

As soon as text is available, the Preview button is activated, with which you can listen to the voice output. Click OK to create a Sound object and insert it into the Timeline.

You will now see the Sound object in the Timeline. You can move or cut the sound object.
 
Right-click on the sound object and Edit spoken language to revise the text and have it spoken again.
 
Click OK to save the object directly and overwrite the existing sound. If you do not want to do this, save the changed sound with a new name. To do this, change the existing file name and click OK.
 
By default, the sounds are saved in the directory that is stored under Extras / Program settings / User directories for the sound output.