Text-to-speech, or TTS, is a technology that converts written text into spoken words.
You can create and customize text-to-speech audio in your project. A single TTS audio track can be up to 500 characters long, which is around 30 seconds of speech, depending on the language and tone. You can create as many TTS tracks as needed, as long as you follow fair usage guidelines.
To add TTS audio to the project, swipe in the bottom bar, tap TTS, and then do the following:
- In the Text to Speech section, select the language and voice from the dropdown lists. Depending on the language, the number of available voices may vary.
- Enter the text you want to convert to speech into the text field (maximum 500 characters).
- Click the Play icon at the bottom left of the text field to listen to the generated speech. Tap Done to finish entering the text.
- Tap Generate at the bottom right of the text field to add the TTS audio to the timeline. The audio track will also be added to Media.
You can customize the TTS audio you created. To edit the track, tap its thumbnail in the timeline, and then do one of the following:
- To edit the text, tap Edit, make the required changes in the text field, tap Done, and then Save.
- To change the volume, click the Volume tab and drag the volume slider.
- To add a fade effect, tap Fade and drag the corresponding sliders.
- To add a copy of the TTS audio, tap Duplicate.
- To remove the TTS element, tap Delete.
- To change the duration of the TTS element, tap Duration and specify the new duration or select one of the presets. Use - or + to shorten or lengthen the track incrementally. Alternatively, in the timeline, drag the yellow handles of the element. Note that a TTS element cannot be extended beyond its original length.