Clone Voice Assets
Last updated
Last updated
Clone Voice Assets: Supports users uploading their voice to clone.
Enter the Clone Voice Assets.
Add Clone Voice: You can upload files from your local storage OR add them from the asset library (only supports video/audio files, with a size limit of 10MB).
The ideal audio length is 1-2 minutes (no less than 1 second), clear with no reverb, defects, or background noise. (Supports audio and video)
Audio quality is the most critical factor affecting cloning results, including the voice itself, language, accent, and recording quality.
Maintain audio consistency to ensure tone and performance remain stable throughout the process.
Ensure moderate volume with an ideal range of -23 dB to -18 dB RMS and a true peak of -3 dB.
After uploading the audio, it supports preview listening, editing the trim time, and the option to remove background music.
Supports custom voice name and description.
After checking the Data Protection Appendix, confirm by clicking Add and wait for the voice recognition to complete.
Once the voice is successfully added, you can click the button to preview and listen (for video files, only the audio will be played).
You can rename the voice, edit the description, and delete the voice.