How do I use the AI Text to Speech (TTS) feature to generate voice overs in CyberLink PowerDirector 365?

In PowerDirector 365 since Apr. 2024, the Text to Speech feature has been added to generate voice overs from Titles, Motion Graphic Titles or Subtitles.

To use the feature, do this:

1. (Multi-)Select the title or motion graphic title clips, or (multi-)select the subtitle markers on the timeline.
2. Click on the Text to Speech button on the timeline toolbar or right-click the selected clips to enter the Text to Speech window.
3. Select a language¹, and then select an audio profile² (Gender, Speaking Style and Use Case) to determine the voice style. You can further adjust the speed and pitch.
4. Click Generate³, and wait for the generation process in the software. The more characters to be produced, the longer the generation process takes.
5. After the generation is complete, close the window and the generated audio will be added to the timeline and the media library automatically.

Note:

1. Supported Languages: English (US/UK​), Chinese​, Japanese​, French​, German​, Korean​, Spanish​, Italian​ & Portuguese. We suggest you choose the same language as the text to avoid generation failure. This feature does not support translation. E.g. English text cannot generate speech in Japanese.
   
2. The real-time preview of your resulting voice over is not supported before generation.
3. AI Text to Speech is a credit-based feature. It consumes credits for the speech generation. If your current credits are insufficient, you can click the Get Credits button in the feature window to purchase additional credits.

---

Related Articles:

1. What are credits?
2. What can I do with the credits on PowerDirector?