HiAPI
kling-ai-avatar 模型详情页 Hero 宽幅图:左侧柔光留白,右侧玻璃头像与胶片光带延伸,冰蓝腮红渐变,名字以发光立体字入画。

Kuaishou

Kling AI Avatar

  • Coming soon

kling-ai-avatar/pro

Audio-driven digital human talking video generation; a single image plus speech is enough to output a lip-synced video, supporting continuous generation of about 5 minutes, with the Standard version at up to 720p

Overview

Introduction coming soon

A detailed guide for this model is being prepared. Pricing, parameters and the API docs below are already available.

kling-ai-avatar/pro is a digital human video generation model in the Kling AI Avatar series. It is a rendering-based talking avatar tool, unlike real-time conversational digital humans: it starts from an input image and audio to generate a lip-synced talking video, rather than performing real-time interaction.

According to the task capabilities officially announced so far, this model covers audio-to-video, avatar-video, image-to-video, and lip-sync, with video as the output type. The same series also offers the kling-ai-avatar/standard version. For specific parameters, maximum resolution, duration limits, and billing, refer to the official launch information.

This model is currently in a coming-soon state, marked as coming_soon on the page, and is not yet available for calls. Once launched, HiAPI.ai will provide access to this model under a unified interface; for specific capability details and request structure, refer to the official launch information.

Related Models

View all models →

Same Type