AI Voice-over

The AI voice-over feature is implemented through artificial intelligence technology and can help users complete creation from text to audio.

Users only need to input text content, then select voice-over settings (language, voice, speed and other elements), and complete voice-over with one click to obtain audio files.

Through this feature, users can quickly create novel audio, news audio and other content.

How to Use

Find the `AI Voice-over` menu in the TransDuck backend, enter this feature, and you can see the specific operation page:

Select Voice

Click the "Select Voice" button on the left to see all available voices, select the desired voice, then click the "Confirm" button.

If you need to use cloned voices of yourself or replicate other sample audio, you can also select "Cloned Voice". If you haven't maintained your own cloned voice yet, first go to Voice Cloning to create your own cloned voice.

Text to Speech

After completing voice selection, users can input the content they want to voice-over in the voice-over content input box on the right to perform voice-over.

If using cloned voices (as shown below), it also supports more detailed speaker style control, including:

• Chinese Dialects: Supports voice-over using Cantonese, Sichuan dialect, Shanghai dialect, Zhengzhou dialect, Changsha dialect, Tianjin dialect, Nanjing dialect, Wuhan dialect and other dialect accents
• Speaking Styles: Supports voice-over using various different tones, including: mysterious, fierce, fearful, curious, sad, happy, surprised, etc.
• Character Imitation: Supports imitating specific characters for voice-over, such as: imitating robots, melancholic poets, majestic ancient generals, etc.