Talking portrait inputs

Kling AI Avatar Standard · Source-framed portrait video
Workflow
Model
Add the required image reference for Kling Avatar.

Required JPG or PNG up to 10 MB. Both sides must be at least 300 pixels and the aspect ratio must stay between 1:2.5 and 2.5:1. Kanvora safety processing caps decoded images at 100 megapixels. EXIF and other image metadata are removed after upload.

Add the required audio reference for Kling Avatar.

Required MP3, WAV, M4A, or AAC from 2 through 300 seconds and up to 5 MB. Server-verified audio duration sets the final credit hold.

Explore every setting now. Sign in only when you are ready to create the request.

5-second estimate before upload · verified 2-300s audio duration sets the hold24 credits

Output proof

Ready for direction

Your first proof starts here

Upload one private portrait image and one private 2-300 second audio file. Verified audio duration sets the exact Standard or Pro credit hold.