Kuaishou · Talking avatars

Kling AI Avatar

Bring a portrait to life with your audio. The model automatically syncs lips and expressions to the speech — a talking avatar up to 5 minutes long.

up to 5 min
Duration
Lip-sync
From audio
from —
credits
720p / 1080p
Quality

How it works

1. Upload a portrait

A photo of a face or character (JPEG/PNG). This is what comes to life and speaks.

2. Upload audio

Speech, voiceover or a voice recording up to 5 minutes. You can record it with a microphone.

3. Get your video

The model syncs lips and expressions to the audio and creates a talking avatar.

Features

Automatic lip-sync to the uploaded audio
Up to 5 minutes of speech — the longest voiceover among all models
Two quality tiers: Standard 720p and Pro 1080p
Perfect for presenters, greetings, explainer videos and virtual hosts
The prompt describes facial expressions and emotions, not the words themselves

Pricing

Standard 720p
0 cr/sec

Price = rate × audio duration

Pro 1080p
0 cr/sec

Maximum facial detail

FAQ

What is Kling AI Avatar?

It's a model that brings a portrait to life using your uploaded audio — creating a talking avatar with automatic lip-sync.

What audio can I upload?

MP3, WAV, AAC, OGG or MP4 with speech/voiceover, up to 5 minutes long. The video length equals the audio length.

Is a text prompt required?

The prompt is optional. It describes the avatar's behavior and emotions — expressions, gaze, nods. The words come from the audio, not the prompt.

How much does it cost?

Pricing is per second: 0 cr/sec for 720p and 0 cr/sec for 1080p, multiplied by the audio duration.

Which language works best for the audio?

The model syncs lips to audio in any language. For the behavior prompt, English works best.

We use cookies to operate the service, keep your session, and collect anonymous statistics. See our Privacy Policy.