Step 1: Upload an image,

Step 2: Input a digital human speech script,

Step 3: Upload an audio file (optional) to customize the voice,

Step 4: Set the video duration

After setting is completed, click run to generate a Sonic digital human lip-sync video effect with one click.

Default settings now: Video duration is 18 seconds, 90 words in the speech script, and approximately 10 minutes to process.

If the video duration increases, the digital human speech script should correspondingly increase, and the processing time will also increase accordingly.