Available now

Kling AI Avatar: talking avatar

By Kuaishou

Kling AI Avatar turns a picture and an audio file into a video of that character speaking or singing along to the audio.

Model ID
Maker
Kuaishou

Input

Fields marked * are required. Review the price before generating.

The image to use as your avatar

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

The URL of the audio file.

Uploading a file needs an account. Create account

MP3, WAV · up to 50 MB

Example prompt. Edit it or write your own.

Price$0.0891 / second

You sign up first. Your settings are kept.

About this model

Overview

Upload an image of a person, an animal, a cartoon or a stylized character, and an audio recording. Kling AI Avatar moves the mouth, face and head in time with the audio, for as long as the recording runs. An optional prompt can steer expression and gestures.

What you can build

  • A talking portrait from a photo and a voice-over
  • A mascot that delivers your announcement
  • Lip-synced song or podcast clips

Prompting tips

  • Use a sharp, front-facing image where the mouth is fully visible.
  • Clean speech without background music gives the closest lip sync.

What to check

Watch the entire clip and compare motion, identity, transitions and audio with your inputs.

Inputs

  • Image (required): The URL of the image to use as your avatar.
  • Audio (required): The URL of the audio file.
  • Prompt (optional): The prompt to use for the video generation.

Output and limits

  • Readable text inside the video, especially small text, is unreliable.
  • Scenes with several interacting characters can lose consistency.
  • Longer clips can show more motion drift or scene changes.
  • Low-quality inputs cause glitches: heavy compression, collages, screenshots and text overlays.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • per second: $0.0891 / second
  • The total for your settings is rounded up to the next cent.