Kuaishou · video
Kling AI Avatar 2.0 Standard
Kling's talking avatar from one photo and an audio, at an affordable price.
Talking photo
- References
- Up to 2 image or audio files
About Kling AI Avatar 2.0 Standard
Kling AI Avatar 2.0 Standard turns a photo and an audio file into a video of the subject speaking it. The provider lists realistic humans, animals, cartoons and stylized characters as subjects. It is Kuaishou's Kling avatar at the Standard tier, priced at $0.15 per second of audio.
For sharper faces and more natural motion at a higher rate, see Kling AI Avatar 2.0 Pro. A typical generation takes about 4 min.
Good for
- Making a photo speak a voice track, for people, animals, cartoons or stylized characters
- Longer talking clips at the lower Kling avatar rate
Getting good results
- The video lasts as long as the audio, so trim silence from the start and end of the track before uploading.
Kling AI Avatar 2.0 Standard questions
What does a Kling AI Avatar 2.0 Standard video cost?
It is priced by the length of the audio: $1.41 for a short line, $8.43 for a full minute.
Do I need to write a prompt?
No. A photo and an audio file are the whole input.